© 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. 44183
    Prev
    Next
    INDEX
    Explanations

    Acronyms or abbreviations

    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
    avyzd
    -0.72
     blown
    -0.71
     Shakspeare
    -0.69
     Cæsar
    -0.67
     Theſe
    -0.66
     maux
    -0.66
     blow
    -0.64
    Климат
    -0.63
     históricas
    -0.63
     ་་
    -0.62
    POSITIVE LOGITS
    PerformLayout
    0.71
    EndInit
    0.63
    ards
    0.61
    logies
    0.60
    doms
    0.59
    rungsseite
    0.58
    skis
    0.58
     of
    0.55
    inSlope
    0.54
    lanes
    0.51
    Activations Density 0.047%

    No Known Activations