© 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. 0-CLT-HP
    7. 95206
    Prev
    Next
    INDEX
    Explanations

    Occ

    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
     continúas
    -0.60
    GRAPHY
    -0.59
     intptr
    -0.57
    ]++;
    -0.56
    脚注の使い方
    -0.56
    InitVars
    -0.56
     CreateTagHelper
    -0.56
     XIV
    -0.54
     Wikidata
    -0.54
     Trusts
    -0.54
    POSITIVE LOGITS
     acciaio
    0.66
     popoli
    0.61
    الإنجليزية
    0.57
    old
    0.54
    DeleteBehavior
    0.54
    endregion
    0.52
     ISNI
    0.52
    anthem
    0.52
     Defect
    0.50
     alluminio
    0.50
    Activations Density 0.971%

    No Known Activations