© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93086
    Prev
    Next
    INDEX
    Explanations

    code or documentation

    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
    SharedCtor
    -0.79
    Identyfik
    -0.68
    ########.
    -0.67
    bewerken
    -0.66
    LookAnd
    -0.66
     ostavi
    -0.64
    ituary
    -0.62
    횟
    -0.62
    ("]");
    -0.60
    Дереккөздер
    -0.59
    POSITIVE LOGITS
    matchCondition
    0.62
    isDebugEnabled
    0.55
     referrerpolicy
    0.55
    ToBounds
    0.54
     colspan
    0.47
    доб
    0.46
     divertimento
    0.45
    BASEPATH
    0.45
    ielded
    0.45
    Pale
    0.45
    Activations Density 0.182%

    No Known Activations