© 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. 44108
    Prev
    Next
    INDEX
    Explanations

    cation

    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
     charged
    -0.64
    charged
    -0.59
     numberOfRows
    -0.55
     Tar
    -0.52
    migrations
    -0.51
    PHI
    -0.49
     Levine
    -0.48
     migration
    -0.48
     Fle
    -0.46
    ionic
    -0.46
    POSITIVE LOGITS
     Monfieur
    0.85
     electrica
    0.77
     Efq
    0.76
    ConstraintMaker
    0.76
     myſelf
    0.74
     ſche
    0.72
     RSSSF
    0.72
     itſelf
    0.69
     canst
    0.68
     serre
    0.67
    Activations Density 0.192%

    No Known Activations