© 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. 10444
    Prev
    Next
    INDEX
    Explanations

    that

    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
     الرياضيه
    -0.72
     Waray
    -0.66
    Personendaten
    -0.65
     Administrativna
    -0.62
    ThroughAttribute
    -0.58
     Italians
    -0.58
     noqa
    -0.57
     Coney
    -0.57
     defaultstate
    -0.56
     Roskov
    -0.56
    POSITIVE LOGITS
     I
    0.69
    UnsafeEnabled
    0.55
    TableModel
    0.55
     webpack
    0.55
    stdc
    0.52
     Maps
    0.52
     (
    0.52
     scales
    0.52
    彡
    0.51
     Scale
    0.50
    Activations Density 0.051%

    No Known Activations