© 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. 1-CLT-HP
    7. 12970
    Prev
    Next
    INDEX
    Explanations

    ogast

    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
    ogast
    -1.30
    #
    -0.70
     Roskov
    -0.68
    //
    -0.68
    FormState
    -0.67
    ulink
    -0.66
    izability
    -0.66
    DrawerToggle
    -0.64
    Portale
    -0.63
    ंदीखरीदारी
    -0.60
    POSITIVE LOGITS
    ren
    0.52
    pexpr
    0.46
    next
    0.46
    ็จ
    0.44
    Next
    0.43
    ɾ
    0.43
    рен
    0.42
    ende
    0.41
    rest
    0.41
    ror
    0.41
    Activations Density 0.006%

    No Known Activations