© 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. 45298
    Prev
    Next
    INDEX
    Explanations

    persist

    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
     importance
    -0.96
     difficulty
    -0.87
     significance
    -0.86
     persistence
    -0.78
     difficulties
    -0.75
     relevance
    -0.74
     usefulness
    -0.71
    enance
    -0.70
    difficulty
    -0.70
     Normdatei
    -0.69
    POSITIVE LOGITS
     of
    0.76
    DebuggerNonUser
    0.56
    onActivityResult
    0.54
    mybatisplus
    0.54
     coming
    0.50
    of
    0.50
    üme
    0.50
    getLogger
    0.50
    DOCTYPE
    0.49
     owed
    0.48
    Activations Density 0.086%

    No Known Activations