© 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. 5-CLT-HP
    7. 95238
    Prev
    Next
    INDEX
    Explanations

    species

    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
    ########.
    -0.98
     ComVisible
    -0.79
    Hentet
    -0.75
    MemoryWarning
    -0.69
    providedIn
    -0.64
    annica
    -0.64
    setContentView
    -0.61
    HandlerContext
    -0.59
     coû
    -0.59
     الرياضيه
    -0.59
    POSITIVE LOGITS
    cipation
    0.48
    frey
    0.45
     wed
    0.45
     infrequently
    0.45
     Kea
    0.44
     native
    0.43
    vieja
    0.42
     Gly
    0.42
     new
    0.41
     Snoop
    0.41
    Activations Density 0.002%

    No Known Activations