© 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. 5-CLT-HP
    7. 92160
    Prev
    Next
    INDEX
    Explanations

    as

    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
     kır
    -0.54
     correlation
    -0.54
     a
    -0.49
    ecore
    -0.49
     steamers
    -0.47
    speaking
    -0.46
    Pyx
    -0.46
     gratitude
    -0.46
     correlations
    -0.46
    исленность
    -0.45
    POSITIVE LOGITS
     שוליים
    0.79
     فريبيس
    0.67
    OGND
    0.58
    XmlEnum
    0.56
    ̍t
    0.55
    oredCriteria
    0.55
    __':
    0.54
     يتيمه
    0.54
    lète
    0.52
    soort
    0.52
    Activations Density 0.005%

    No Known Activations