© 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. 1-CLT-HP
    7. 14857
    Prev
    Next
    INDEX
    Explanations

    passage escape

    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
    WriteBarrier
    -0.66
    DoubleQuotes
    -0.65
    enterOuterAlt
    -0.64
     BoxFit
    -0.62
    fromnode
    -0.62
    bootstrapcdn
    -0.61
    DOCTYPE
    -0.61
    <tfoot>
    -0.60
    oredCriteria
    -0.60
    djangoproject
    -0.59
    POSITIVE LOGITS
     Roper
    0.54
    bege
    0.50
    циони
    0.50
     up
    0.47
     particulier
    0.47
    յ
    0.47
    次代
    0.46
    ers
    0.46
    up
    0.45
    ness
    0.45
    Activations Density 0.005%

    No Known Activations