© 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. 2029
    Prev
    Next
    INDEX
    Explanations

    phrases related to imagining possibilities or scenarios

    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
    1624
    +0.18
    0.6%
    899
    +0.15
    0.5%
    196
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1624
    +0.18
    0.04
    899
    +0.15
    0.04
    196
    +0.14
    0.03
    Negative Logits
     Henk
    -0.58
     exé
    -0.57
     Tanja
    -0.56
     caract
    -0.56
     clearness
    -0.55
     étu
    -0.55
     Utiliza
    -0.55
    Caratter
    -0.53
     reluct
    -0.52
     défend
    -0.51
    POSITIVE LOGITS
     imagine
    1.17
    imagine
    1.06
     Imagine
    0.97
     imagining
    0.94
    Imagine
    0.93
     imagined
    0.90
    imagining
    0.88
     imagines
    0.84
     imagin
    0.82
    imagined
    0.77
    Activations Density 0.090%

    No Known Activations