© 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. 12204
    Prev
    Next
    INDEX
    Explanations

    Internet Explorer

    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
     Kek
    -0.74
    MemoryWarning
    -0.55
    Kek
    -0.52
    igor
    -0.49
     CURIAM
    -0.47
     Dox
    -0.47
     disambiguazione
    -0.47
     DOM
    -0.47
     PAC
    -0.47
     Balik
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.84
    ed
    0.66
    "}")
    0.52
    /***/
    0.51
    UnusedPrivate
    0.50
    ValueStyle
    0.49
    andReturn
    0.49
    الإنجليزية
    0.49
     Polsek
    0.49
    Bonsoir
    0.49
    Activations Density 0.007%

    No Known Activations