© 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. 45103
    Prev
    Next
    INDEX
    Explanations

    Penalty

    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
     penalty
    -1.04
     penalties
    -0.96
     abandon
    -0.84
     Penalties
    -0.82
     Penalty
    -0.81
     Abandon
    -0.80
     abandoning
    -0.79
     violate
    -0.77
    abandon
    -0.76
     violates
    -0.75
    POSITIVE LOGITS
    ItemBackground
    0.68
    agno
    0.53
    HasAnnotation
    0.52
    аз
    0.50
    يكب
    0.50
    はじめに
    0.50
     yön
    0.50
    iastes
    0.50
    retum
    0.49
    support
    0.48
    Activations Density 1.625%

    No Known Activations