© 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. 44192
    Prev
    Next
    INDEX
    Explanations

    Works

    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
    Works
    -2.02
     works
    -1.95
     Works
    -1.94
    works
    -1.88
     WORKS
    -1.66
    WORKS
    -1.62
     œuvres
    -0.95
     obras
    -0.93
     acts
    -0.84
     auroit
    -0.81
    POSITIVE LOGITS
     дописавши
    0.73
     CURIAM
    0.71
    intios
    0.71
    heets
    0.69
     بيها
    0.65
    Tikang
    0.64
    ]")]
    0.63
     متحده
    0.62
    hips
    0.61
     baseman
    0.60
    Activations Density 0.310%

    No Known Activations