© 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. 92086
    Prev
    Next
    INDEX
    Explanations

    technical documents and names

    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
     Levine
    -1.15
    cule
    -0.91
    orology
    -0.90
    tonsoft
    -0.69
     للمعارف
    -0.64
    Discuss
    -0.63
     achieving
    -0.59
     giudizio
    -0.58
     Obs
    -0.57
    cules
    -0.57
    POSITIVE LOGITS
    ities
    0.49
    허
    0.46
     kasarigan
    0.45
    derung
    0.44
     Unsc
    0.43
    SerializeField
    0.42
     Parenthood
    0.42
    ients
    0.41
    Unset
    0.41
     Meksiku
    0.41
    Activations Density 1.232%

    No Known Activations