Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91871
    Prev
    Next
    INDEX
    Explanations

    cycle

    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
     cycle
    -0.66
     Cycle
    -0.62
    cycle
    -0.61
    Cycle
    -0.59
    Personensuche
    -0.57
     CYCLE
    -0.55
     OMITBAD
    -0.50
    ьаж
    -0.48
    サイクル
    -0.47
    ESIS
    -0.46
    POSITIVE LOGITS
     itſelf
    0.79
     themſelves
    0.74
     Efq
    0.74
    σθαι
    0.73
     purpoſe
    0.73
     whoſe
    0.73
     myſelf
    0.72
     himſelf
    0.71
     poffible
    0.71
    GraphicsUnit
    0.69
    Activations Density 0.078%

    No Known Activations