© 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. 39855
    Prev
    Next
    INDEX
    Explanations

    good

    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
     blessés
    -0.82
     good
    -0.79
     lèvres
    -0.69
     vœux
    -0.69
     prisonniers
    -0.68
     meilleures
    -0.66
    good
    -0.64
     vérit
    -0.64
     ostavi
    -0.63
     preuves
    -0.63
    POSITIVE LOGITS
    Tikang
    0.63
    InvalidProtocol
    0.63
    BeginContext
    0.54
     Efq
    0.54
    stdc
    0.52
     representations
    0.50
    setVerticalGroup
    0.50
     nephe
    0.49
     analogs
    0.49
     algorithms
    0.48
    Activations Density 0.023%

    No Known Activations