© 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. 2194
    Prev
    Next
    INDEX
    Explanations

    declining trends or situations over time

    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
    506
    +0.13
    0.5%
    1325
    +0.12
    0.4%
    316
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1325
    +0.13
    0.02
    316
    +0.12
    0.02
    1506
    +0.11
    0.02
    Negative Logits
     accanto
    -0.64
     Hermans
    -0.57
     expor
    -0.54
     revan
    -0.54
     piú
    -0.53
     prouve
    -0.53
     perciò
    -0.53
     Ivo
    -0.52
     esattamente
    -0.52
     MOP
    -0.52
    POSITIVE LOGITS
     decline
    1.09
     declines
    1.00
     Decline
    1.00
     declined
    0.97
     declining
    0.92
    Decline
    0.90
    decline
    0.87
     decl
    0.66
    decl
    0.66
     scă
    0.61
    Activations Density 0.091%

    No Known Activations