© 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. 22420
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant involvement or roles in various contexts

    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
    iy
    -0.52
    yntaxException
    -0.52
    steamcommunity
    -0.51
    </table>
    -0.50
     selera
    -0.49
     sh
    -0.47
    ższy
    -0.47
    дження
    -0.46
     Free
    -0.46
    時
    -0.46
    POSITIVE LOGITS
    StructEnd
    0.85
     виправивши
    0.84
     >=",
    0.81
    IntoConstraints
    0.81
    ftagPool
    0.76
     rôle
    0.75
     ModelExpression
    0.73
     MainAxisSize
    0.73
    expandindo
    0.72
     BoxDecoration
    0.71
    Activations Density 0.015%

    No Known Activations