© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7394
    Prev
    Next
    INDEX
    Explanations

    phrases related to managing or controlling a situation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    690
    +0.10
    0.3%
    890
    +0.09
    0.3%
    687
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    890
    +0.10
    0.03
    11
    +0.09
    0.03
    1407
    +0.09
    0.02
    Negative Logits
     ▶
    -0.56
     palab
    -0.52
     appartient
    -0.52
     colombia
    -0.52
     karton
    -0.51
     balon
    -0.51
     Cien
    -0.50
     préc
    -0.50
     Cita
    -0.49
     prendra
    -0.49
    POSITIVE LOGITS
     successfully
    0.77
     managed
    0.72
     manage
    0.69
     manages
    0.61
    Successfully
    0.61
     miraculously
    0.59
    successfully
    0.59
     conseguiu
    0.58
     successful
    0.58
     somehow
    0.58
    Activations Density 0.196%

    No Known Activations