© 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. 5-CLT-HP
    7. 92229
    Prev
    Next
    INDEX
    Explanations

    voltage and circuits

    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
     novios
    -0.44
    lihood
    -0.41
     ligiloj
    -0.39
    ußer
    -0.37
    miljø
    -0.36
    neval
    -0.36
    ("-",
    -0.36
     confusión
    -0.36
    ^(
    -0.36
    intl
    -0.36
    POSITIVE LOGITS
    InjectAttribute
    0.83
    +#+#
    0.78
    Personendaten
    0.72
    StreetMap
    0.68
    Datuak
    0.68
    HandlerContext
    0.66
    SBATCH
    0.66
     חיצוניים
    0.66
    rawDesc
    0.63
    LookAnd
    0.63
    Activations Density 0.001%

    No Known Activations