© 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. 12-RES-MATRYOSHKA-DC
    7. 3157
    Prev
    Next
    INDEX
    Explanations

    information related to demographic or categorical characteristics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    MessageOf
    -1.00
     تضيفلها
    -0.84
    findpost
    -0.82
    ,:);
    -0.77
     وتسجيلات
    -0.77
     Audiodateien
    -0.77
    ArgsConstructor
    -0.74
    DNEY
    -0.72
     الحره
    -0.71
     UnityEditor
    -0.71
    POSITIVE LOGITS
    Externí
    0.54
     подо
    0.49
    InputTagHelper
    0.49
    AutoScaleMode
    0.48
     Aitken
    0.48
     الب
    0.47
     bed
    0.46
    bed
    0.46
     jár
    0.46
     rival
    0.46
    Activations Density 0.087%

    No Known Activations