© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75411
    Prev
    Next
    INDEX
    Explanations

    Research and publications

    np_max-act-logits · 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
     Anſ
    -0.70
    findpost
    -0.69
     Houſe
    -0.66
     Diſ
    -0.66
     houſe
    -0.65
    tvguidetime
    -0.65
     pleaſure
    -0.65
    GEBURTSDATUM
    -0.65
     jspb
    -0.64
     tslint
    -0.63
    POSITIVE LOGITS
    tholes
    0.32
    cades
    0.32
     formulate
    0.31
    ốm
    0.31
    culated
    0.30
    haber
    0.29
     plans
    0.29
     blocks
    0.29
    wikidata
    0.29
    ABASES
    0.28
    Activations Density 0.006%

    No Known Activations