© 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. 9993
    Prev
    Next
    INDEX
    Explanations

    Bonham

    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
     تضيفلها
    -0.95
    RenderAtEndOf
    -0.77
    TypedDataSet
    -0.72
     виправивши
    -0.71
     resourceCulture
    -0.69
    DeleteBehavior
    -0.66
     définiti
    -0.65
    GEBURTSDATUM
    -0.64
    ViewFeatures
    -0.64
     }{@
    -0.62
    POSITIVE LOGITS
     Ανακτήθηκε
    0.58
     /\.
    0.56
    UnknownFields
    0.52
    age
    0.50
     reper
    0.49
    ign
    0.49
    ivo
    0.47
    Aware
    0.46
     Vain
    0.46
     Alter
    0.46
    Activations Density 0.022%

    No Known Activations