© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 881
    Prev
    Next
    INDEX
    Explanations

    case

    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
    featureID
    -0.81
    ConstraintMaker
    -0.80
    providedIn
    -0.77
    ]--;
    -0.76
     AttributeSet
    -0.74
    chaffenheit
    -0.71
    AnchorStyles
    -0.69
    NameInMap
    -0.68
     DialogResult
    -0.67
    WireFormatLite
    -0.67
    POSITIVE LOGITS
    full
    0.48
     fá
    0.44
    count
    0.43
    base
    0.43
    times
    0.43
    loc
    0.42
    time
    0.41
    -
    0.39
    pero
    0.39
     basic
    0.38
    Activations Density 0.001%

    No Known Activations