© 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. 4-CLT-HP
    7. 4520
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    MigrationBuilder
    -0.97
     feroit
    -0.96
     propOrder
    -0.94
     avoient
    -0.93
    حياته
    -0.92
     auroit
    -0.92
     étoient
    -0.85
     anún
    -0.84
     pouvoit
    -0.83
    __":
    -0.82
    POSITIVE LOGITS
     the
    0.80
    ,
    0.66
     a
    0.64
     an
    0.55
     compar
    0.52
     always
    0.52
    ...
    0.51
    .
    0.51
     #
    0.50
     "
    0.49
    Activations Density 0.009%

    No Known Activations