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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2503
    Prev
    Next
    INDEX
    Explanations

    the word "those."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.63
    ly
    -0.60
    первых
    -0.59
     and
    -0.58
    وفاته
    -0.57
     "]";
    -0.53
     itself
    -0.50
    öte
    -0.50
    lijf
    -0.49
     deltaTime
    -0.49
    POSITIVE LOGITS
     belonging
    0.84
     who
    0.84
     يتيمه
    0.83
     pesky
    0.82
    genen
    0.77
    RenderAtEndOf
    0.71
     Which
    0.71
     ones
    0.70
    Which
    0.70
    jenigen
    0.69
    Activations Density 0.064%

    No Known Activations