© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92096
    Prev
    Next
    INDEX
    Explanations

    what

    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
    ThroughAttribute
    -1.08
    脚注の使い方
    -1.05
    rungsseite
    -1.05
     متعلقه
    -1.04
    دانشنامهٔ
    -1.02
     Numerade
    -0.96
    ьаж
    -0.94
     invokingState
    -0.92
    tvguidetime
    -0.92
    ConstraintMaker
    -0.92
    POSITIVE LOGITS
    '
    1.09
    ’
    0.97
    ↵↵
    0.87
    "
    0.81
    1
    0.78
    2
    0.76
    ‘
    0.75
    ↵
    0.71
     
    0.69
    <bos>
    0.69
    Activations Density 1.042%

    No Known Activations