© 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. 1-CLT-HP
    7. 15051
    Prev
    Next
    INDEX
    Explanations

    of

    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
    DockStyle
    -0.77
    TintMode
    -0.69
    клопе
    -0.68
    ſtanding
    -0.67
    hematical
    -0.66
    RectangleBorder
    -0.66
     ProtoMessage
    -0.66
    rrggbb
    -0.65
    सन्दर्भ
    -0.64
    haustible
    -0.64
    POSITIVE LOGITS
     teme
    0.41
     potato
    0.40
     vegetables
    0.40
     veggies
    0.39
     carrots
    0.39
     pumpkin
    0.39
     beans
    0.38
     cheesecake
    0.38
     produce
    0.37
     chicken
    0.37
    Activations Density 0.027%

    No Known Activations