© 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. 1223
    Prev
    Next
    INDEX
    Explanations

    I

    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
    I
    -1.78
     I
    -0.93
     sacré
    -0.62
     sauvages
    -0.61
     kvinder
    -0.61
     culturali
    -0.61
     étrangère
    -0.61
     millioner
    -0.60
     becauſe
    -0.60
     conmigo
    -0.59
    POSITIVE LOGITS
     surla
    0.97
     have
    0.82
     يتيمه
    0.78
     дописавши
    0.77
     feel
    0.75
    ELTS
    0.75
     am
    0.74
    WithIOException
    0.74
     want
    0.73
     will
    0.71
    Activations Density 0.533%

    No Known Activations