© 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. 20-CLT-HP
    7. 77475
    Prev
    Next
    INDEX
    Explanations

    Code and technical text

    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
     TestBed
    -0.63
    chium
    -0.62
    IsPostBack
    -0.60
    setVerticalGroup
    -0.56
     riten
    -0.56
    THROUGH
    -0.54
    rdom
    -0.54
    Билгалдахарш
    -0.52
    Mutagenicity
    -0.51
    herin
    -0.50
    POSITIVE LOGITS
     to
    1.32
    to
    0.64
    tobe
    0.63
    WireFormat
    0.56
    atimes
    0.54
    ToBe
    0.53
     να
    0.52
     '\\;'
    0.52
    到
    0.50
     TO
    0.48
    Activations Density 0.000%

    No Known Activations