© 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. 4987
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
     cá
    -0.53
    ::::::::
    -0.48
     Cia
    -0.43
    bind
    -0.42
    AMENT
    -0.42
    Dat
    -0.42
     ida
    -0.41
     seguenti
    -0.41
     Geden
    -0.40
     Dat
    -0.40
    POSITIVE LOGITS
     المعيارى
    0.89
    styleUrls
    0.76
     GenerationType
    0.71
    WebVitals
    0.71
     cauſe
    0.71
     reafon
    0.70
     незавершена
    0.68
    addGap
    0.68
     argc
    0.67
    contentLoaded
    0.66
    Activations Density 0.000%

    No Known Activations