© 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. 5142
    Prev
    Next
    INDEX
    Explanations

    abbreviations/initials

    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
     kysy
    -0.68
     čierna
    -0.57
     disponibilités
    -0.56
     jäsen
    -0.56
    hdashline
    -0.56
     epä
    -0.55
     vägen
    -0.55
    pozorn
    -0.54
     hanem
    -0.54
     conquête
    -0.54
    POSITIVE LOGITS
     שוליים
    0.61
    لينكات
    0.59
     Alembic
    0.58
    .*")]
    0.57
     كومونز
    0.55
    newArrayList
    0.53
     organizers
    0.53
     חיצוניים
    0.53
     PropTypes
    0.53
     سكانية
    0.52
    Activations Density 0.001%

    No Known Activations