© 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. 811
    Prev
    Next
    INDEX
    Explanations

    shortages

    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
     pesados
    -0.55
    idora
    -0.55
     Circuit
    -0.54
     CIRCUIT
    -0.52
    STREAM
    -0.51
    linearGradient
    -0.50
    IALES
    -0.50
     Flushing
    -0.49
     Circuits
    -0.49
    ISING
    -0.48
    POSITIVE LOGITS
    <bos>
    0.69
    localctx
    0.57
    yntaxException
    0.56
    DockStyle
    0.54
    MemoryWarning
    0.54
    InjectAttribute
    0.53
    Personendaten
    0.51
    MigrationBuilder
    0.50
    Билгалдахарш
    0.50
    UrlResolution
    0.49
    Activations Density 0.015%

    No Known Activations