© 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. 24869
    Prev
    Next
    INDEX
    Explanations

    elements related to expertise and uniqueness in a technical or competitive context

    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
     directions
    -0.44
     also
    -0.42
    しても
    -0.41
    lagt
    -0.41
    Попис
    -0.40
     rağmen
    -0.39
    Dir
    -0.39
    urs
    -0.37
    dir
    -0.37
     outro
    -0.37
    POSITIVE LOGITS
    MigrationBuilder
    0.86
     HasFactory
    0.79
    存于互联网档案馆
    0.78
    mphony
    0.73
     AssemblyCompany
    0.71
    ">//
    0.71
     pulumi
    0.71
     يتيمه
    0.71
     hObject
    0.71
    )))),
    0.68
    Activations Density 0.056%

    No Known Activations