© 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. 4-CLT-HP
    7. 880
    Prev
    Next
    INDEX
    Explanations

    role

    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
    CloseOperation
    -0.71
    onViewCreated
    -0.71
    ніципалі
    -0.66
    Tikang
    -0.63
    addCriterion
    -0.63
     autorytatywna
    -0.60
     समीक्षक
    -0.60
    ufnahme
    -0.57
    igraphic
    -0.57
    hatikan
    -0.56
    POSITIVE LOGITS
    x
    0.65
    ty
    0.62
    ta
    0.51
    page
    0.51
    tt
    0.50
    td
    0.49
    WaitGroup
    0.47
    Ta
    0.46
    ties
    0.46
    ist
    0.45
    Activations Density 0.004%

    No Known Activations