© 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. 20-CLT-HP
    7. 77061
    Prev
    Next
    INDEX
    Explanations

    Mixed, technical content

    np_max-act-logits · 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
    ंदीखरीदारी
    -0.97
    #+#
    -0.73
    MessageTagHelper
    -0.71
    intios
    -0.66
    parsedMessage
    -0.64
     poveznice
    -0.64
    MENAFN
    -0.63
    >`;
    -0.63
    Rhestr
    -0.63
     Era
    -0.63
    POSITIVE LOGITS
    makeConstraints
    0.45
    migrationBuilder
    0.44
    ospor
    0.43
    adaptiveStyles
    0.39
    ással
    0.35
    ConstraintMaker
    0.34
     än
    0.34
     (°
    0.33
     UIApplication
    0.32
     rut
    0.32
    Activations Density 0.000%

    No Known Activations