© 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. 0-CLT-HP
    7. 45118
    Prev
    Next
    INDEX
    Explanations

    persuasive expression

    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
     comprehensive
    -0.78
    comprehensive
    -0.76
    complete
    -0.67
     rispet
    -0.66
    TestingModule
    -0.64
     виправивши
    -0.64
    rid
    -0.63
    tr
    -0.62
    Comprehensive
    -0.62
    sto
    -0.60
    POSITIVE LOGITS
    RenderAtEndOf
    0.61
    oient
    0.56
    crapers
    0.54
    NEO
    0.53
    ofold
    0.52
    casila
    0.52
     doubtnut
    0.50
    bonucleic
    0.50
    =$?
    0.50
    StandardCharsets
    0.50
    Activations Density 0.229%

    No Known Activations