© 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. 14861
    Prev
    Next
    INDEX
    Explanations

    availability

    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
    IntoConstraints
    -0.82
    TargetException
    -0.77
    StoryboardSegue
    -0.72
     <<<<<<<<<<<<<<
    -0.71
    حياتها
    -0.71
    PhysRevLett
    -0.69
     ब्रेकडाउन
    -0.66
    GeneratedCode
    -0.66
    CloseOperation
    -0.65
    ApiModel
    -0.65
    POSITIVE LOGITS
    ępnie
    0.39
     cạnh
    0.39
    apropri
    0.37
    Становништво
    0.37
     juntamente
    0.37
     perche
    0.35
     poiché
    0.35
     strany
    0.34
     lẫn
    0.34
     novios
    0.34
    Activations Density 0.007%

    No Known Activations