© 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. 97492
    Prev
    Next
    INDEX
    Explanations

    mate

    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
     cast
    -1.30
    cast
    -1.11
     Cast
    -0.97
    mate
    -0.86
    Cast
    -0.85
     mate
    -0.85
    casts
    -0.83
     divers
    -0.72
    mates
    -0.71
    CAST
    -0.68
    POSITIVE LOGITS
     Shakspeare
    1.09
     itſelf
    1.04
     myſelf
    0.96
    ftagPool
    0.89
     Shaksp
    0.88
     againſt
    0.85
     Majefty
    0.84
     Saxon
    0.82
     pleaſure
    0.82
     negroes
    0.82
    Activations Density 0.190%

    No Known Activations