© 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. 5-CLT-HP
    7. 91349
    Prev
    Next
    INDEX
    Explanations

    suppose

    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
     podjela
    -0.63
     sobą
    -0.58
     yourself
    -0.57
     yourselves
    -0.49
     Sélectionnez
    -0.48
     Presumably
    -0.48
    yourself
    -0.46
     مشين
    -0.46
     YOURSELF
    -0.45
     způ
    -0.44
    POSITIVE LOGITS
     also
    0.69
     that
    0.66
     furthermore
    0.65
     additionally
    0.63
     moreover
    0.63
     further
    0.59
     we
    0.56
    +#+
    0.55
     enfin
    0.52
    UVWXYZ
    0.52
    Activations Density 0.022%

    No Known Activations