© 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. 4-CLT-HP
    7. 1718
    Prev
    Next
    INDEX
    Explanations

    info

    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
    المناصب
    -0.44
     về
    -0.42
    Merkmale
    -0.40
    évaluateur
    -0.39
    Билгалдахарш
    -0.36
     nakalista
    -0.35
    tainty
    -0.35
    MessageState
    -0.35
    bellar
    -0.35
    تري
    -0.35
    POSITIVE LOGITS
    %)$
    0.69
    uxxxx
    0.68
    DockStyle
    0.68
    gdx
    0.66
    findpost
    0.65
    migrationBuilder
    0.63
    tvguidetime
    0.63
    ResumeLayout
    0.61
    gettyimages
    0.60
    URLException
    0.60
    Activations Density 0.008%

    No Known Activations