© 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. 3256
    Prev
    Next
    INDEX
    Explanations

    numerical data or figures related to studies

    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
    expandindo
    -0.65
    ouncil
    -0.65
    xox
    -0.64
    aarrggbb
    -0.63
    енча
    -0.60
    æus
    -0.56
    bigcup
    -0.55
     ویکی‌پدیای
    -0.55
    aulted
    -0.55
    Personendaten
    -0.54
    POSITIVE LOGITS
     صوتيه
    0.60
    findpost
    0.51
    出版年
    0.49
    WireFormat
    0.45
     aDecoder
    0.45
    endregion
    0.45
    weds
    0.44
     ferie
    0.42
     vettoriale
    0.42
     craindre
    0.41
    Activations Density 0.235%

    No Known Activations