© 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. 5-CLT-HP
    7. 91155
    Prev
    Next
    INDEX
    Explanations

    tables and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.62
     ModelRenderer
    -0.58
    rooms
    -0.52
    dens
    -0.51
    sec
    -0.51
     ninh
    -0.51
     članak
    -0.50
    </thead>
    -0.49
    from
    -0.49
    ros
    -0.49
    POSITIVE LOGITS
    Rhestr
    0.69
    EnumMember
    0.57
     مشين
    0.57
    EndInit
    0.55
     protoimpl
    0.53
    čiau
    0.53
    OrBuilder
    0.53
     @"/
    0.52
    quehanna
    0.52
    StructEnd
    0.50
    Activations Density 0.002%

    No Known Activations