© 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. 91130
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    UpInside
    -0.68
    reasons
    -0.65
     purpoſe
    -0.64
    extAlignment
    -0.62
     reasons
    -0.61
    casian
    -0.60
    ACTERS
    -0.57
     useParams
    -0.57
    ArgsConstructor
    -0.57
    ruptcy
    -0.56
    POSITIVE LOGITS
     ProtoMessage
    0.56
     of
    0.48
     
    0.47
     Enough
    0.46
     half
    0.45
    protoimpl
    0.45
     four
    0.44
     infancy
    0.44
    gefü
    0.44
     two
    0.44
    Activations Density 0.015%

    No Known Activations