© 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. 1-CLT-HP
    7. 9114
    Prev
    Next
    INDEX
    Explanations

    in

    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
    цездатний
    -0.62
    PLAY
    -0.58
     strto
    -0.58
    rrggbb
    -0.57
    fjspx
    -0.56
    typeorm
    -0.56
    routeProvider
    -0.56
    χν
    -0.55
    ₂+
    -0.54
     iconFacebook
    -0.54
    POSITIVE LOGITS
    <bos>
    0.56
     Polsek
    0.51
    évaluateur
    0.51
     dalamnya
    0.48
    AsUp
    0.47
    contentLoaded
    0.44
     pelaku
    0.42
    تقاوى
    0.42
    untung
    0.41
     généraux
    0.40
    Activations Density 0.062%

    No Known Activations