Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12501
    Prev
    Next
    INDEX
    Explanations

    servers

    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
    UNITY
    -0.55
    นด์
    -0.53
    iNdEx
    -0.52
    icep
    -0.52
    LEEP
    -0.52
    Poz
    -0.52
     Сме
    -0.51
     panoramique
    -0.51
    dialement
    -0.50
    mState
    -0.50
    POSITIVE LOGITS
    帖最后由
    0.63
    hit
    0.55
    quelize
    0.53
    Smarty
    0.52
     ModelExpression
    0.50
    JspWriter
    0.50
    ächtig
    0.50
    sequelize
    0.48
    ^(@)
    0.48
    Personendaten
    0.48
    Activations Density 0.009%

    No Known Activations