© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40296
    Prev
    Next
    INDEX
    Explanations

    Pret

    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
    ed
    -0.70
    atoria
    -0.63
    eing
    -0.49
    iac
    -0.48
    ッキリ
    -0.48
    earing
    -0.48
    edale
    -0.48
    effectiveness
    -0.47
    icted
    -0.47
    dings
    -0.45
    POSITIVE LOGITS
    EDEFAULT
    0.68
    EndGlobalSection
    0.68
    AlterField
    0.66
    tagext
    0.65
    ANTLR
    0.64
    brainly
    0.64
     Arhivirano
    0.64
    PullParser
    0.63
     resultCode
    0.63
    multer
    0.62
    Activations Density 0.214%

    No Known Activations