© 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. 14905
    Prev
    Next
    INDEX
    Explanations

    very

    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
    <bos>
    -0.61
    tvguidetime
    -0.49
     latest
    -0.47
    ktop
    -0.46
    béco
    -0.46
    rawDesc
    -0.46
     HttpNotFound
    -0.44
     recent
    -0.41
    ify
    -0.41
    ification
    -0.40
    POSITIVE LOGITS
    ngdoc
    0.69
    ftance
    0.65
    ThroughAttribute
    0.65
    latego
    0.63
    reportError
    0.63
    rinology
    0.62
    WebElementEntity
    0.61
    Referencer
    0.60
     Stunde
    0.59
     Delano
    0.59
    Activations Density 0.012%

    No Known Activations