© 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. 45095
    Prev
    Next
    INDEX
    Explanations

    Avoiding problems

    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
     forth
    -0.75
    ved
    -0.71
    forth
    -0.69
    led
    -0.69
    mon
    -0.66
     distract
    -0.59
     distracting
    -0.57
     mon
    -0.56
     distractions
    -0.55
     Mon
    -0.52
    POSITIVE LOGITS
     resourceCulture
    0.99
     ―――――
    0.97
     itſelf
    0.94
     myſelf
    0.93
    AndEndTag
    0.89
     iconTwitter
    0.88
     propOrder
    0.86
     Jefus
    0.84
     Anſ
    0.83
     poffible
    0.83
    Activations Density 0.091%

    No Known Activations