© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13192
    Prev
    Next
    INDEX
    Explanations

    SH

    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
     Paglinawan
    -0.75
    gonic
    -0.75
    
    -0.68
    ])):
    -0.63
    Kung
    -0.63
     Réponses
    -0.63
     Kung
    -0.63
    IntoConstraints
    -0.62
     grà
    -0.60
    ftagPool
    -0.60
    POSITIVE LOGITS
     of
    0.47
    unea
    0.46
    rse
    0.46
    UAWEI
    0.45
     stable
    0.45
     pro
    0.44
    ucco
    0.44
     René
    0.43
     reputed
    0.43
     PRO
    0.43
    Activations Density 0.026%

    No Known Activations