© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 22790
    Prev
    Next
    INDEX
    Explanations

    expressions related to biological signaling and cellular interactions

    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
    Negative Logits
     blancas
    -0.47
     nahilalakip
    -0.47
     brancas
    -0.45
     schade
    -0.44
    XmlRootElement
    -0.44
     kuid
    -0.44
     vidare
    -0.43
    ed
    -0.42
    łuż
    -0.42
     passaggio
    -0.42
    POSITIVE LOGITS
    kháu
    0.78
    Становништво
    0.74
    actionMode
    0.69
    endphp
    0.66
     StatelessWidget
    0.65
    amssymb
    0.63
    lapsingToolbar
    0.60
    zzleHttp
    0.59
    tvguidetime
    0.59
     كومونز
    0.58
    Activations Density 0.654%

    No Known Activations