© 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. 72200
    Prev
    Next
    INDEX
    Explanations

    Beginning of lines

    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
    RetentionPolicy
    -0.59
    StatusOK
    -0.53
    CloseOperation
    -0.53
    OrBuilder
    -0.52
    MessageTagHelper
    -0.52
    tichetta
    -0.50
     [*]
    -0.48
     TextAlign
    -0.48
    subplots
    -0.47
    propTypes
    -0.46
    POSITIVE LOGITS
    脚注の使い方
    0.74
     horizon
    0.60
    ()?;
    0.54
    tvguidetime
    0.54
    UnusedPrivate
    0.52
    IInterface
    0.52
    Aper
    0.50
    IndentedString
    0.50
    זור
    0.49
     Half
    0.49
    Activations Density 0.000%

    No Known Activations