© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93915
    Prev
    Next
    INDEX
    Explanations

    ponds

    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
     Theſe
    -1.16
     myſelf
    -1.16
     Roskov
    -1.15
     itſelf
    -1.09
     Administrativna
    -1.06
     betweenstory
    -1.04
     Reſ
    -1.02
     purpoſe
    -1.00
     iſt
    -1.00
     Efq
    -0.94
    POSITIVE LOGITS
    ,
    0.86
     in
    0.82
    .
    0.79
     and
    0.77
     for
    0.77
     with
    0.75
     (
    0.72
     to
    0.69
     that
    0.67
     
    0.67
    Activations Density 0.599%

    No Known Activations