© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95236
    Prev
    Next
    INDEX
    Explanations

    bears

    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
     autorytatywna
    -0.81
    ValueStyle
    -0.77
    ViewFeatures
    -0.75
    TabIndex
    -0.69
    RUnlock
    -0.61
    CppMethod
    -0.60
    SequentialGroup
    -0.59
    TextSpan
    -0.59
    databind
    -0.58
    ,‎
    -0.57
    POSITIVE LOGITS
     two
    0.51
     quitte
    0.45
    Footnotes
    0.45
     capitales
    0.44
     čás
    0.44
     steps
    0.43
     slight
    0.43
    two
    0.42
    一出
    0.42
     branches
    0.42
    Activations Density 0.004%

    No Known Activations