© 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. 0-CLT-HP
    7. 95562
    Prev
    Next
    INDEX
    Explanations

    bodies

    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
    Negative Logits
     bodies
    -1.98
    bodies
    -1.53
     Bodies
    -1.51
    Bodies
    -1.16
    files
    -1.04
     files
    -0.97
     body
    -0.95
     cuerpos
    -0.95
    body
    -0.86
     corpi
    -0.82
    POSITIVE LOGITS
    IntoConstraints
    0.92
    StoreMessageInfo
    0.85
    expandindo
    0.80
    UnitTesting
    0.77
    
    0.77
    DebuggerNonUser
    0.74
    AndEndTag
    0.73
     ujednoznacz
    0.72
    ArgsConstructor
    0.69
    
    0.69
    Activations Density 0.099%

    No Known Activations