© 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. 0-CLT-HP
    7. 94216
    Prev
    Next
    INDEX
    Explanations

    Double

    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
    double
    -0.63
     double
    -0.63
     DOUBLE
    -0.57
    antart
    -0.55
    InstanceState
    -0.53
    GraphicsUnit
    -0.52
     Bacteriol
    -0.52
    タジー
    -0.50
    Double
    -0.50
     doble
    -0.49
    POSITIVE LOGITS
    henge
    0.58
     ujednoznacz
    0.56
    dí
    0.54
     Aviv
    0.54
    ectoria
    0.53
    gated
    0.52
    tà
    0.52
    ratore
    0.52
    _),
    0.52
    withstanding
    0.50
    Activations Density 0.118%

    No Known Activations