© 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. 5-CLT-HP
    7. 2303
    Prev
    Next
    INDEX
    Explanations

    choose

    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
    kuuta
    -0.48
     بش
    -0.45
    subs
    -0.45
    ress
    -0.44
    inguished
    -0.44
    stoffen
    -0.42
     materialize
    -0.41
    имущества
    -0.41
     bien
    -0.41
    viaf
    -0.40
    POSITIVE LOGITS
     Paglinawan
    0.81
    Personensuche
    0.71
    __(/*!
    0.69
    SBATCH
    0.68
    styleType
    0.68
    findpost
    0.66
     leſs
    0.65
    parsedMessage
    0.65
    limo
    0.64
    fillType
    0.63
    Activations Density 0.003%

    No Known Activations