© 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. 10178
    Prev
    Next
    INDEX
    Explanations

    consequence

    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
    ineno
    -0.62
    iers
    -0.60
    ers
    -0.59
    BoxShadow
    -0.58
    AxisAlignment
    -0.54
    erd
    -0.53
    laken
    -0.52
    erez
    -0.51
    iem
    -0.49
     cré
    -0.49
    POSITIVE LOGITS
    évaluateur
    0.57
    tagHelper
    0.57
     متعلقه
    0.56
    AutoScaleMode
    0.53
    AsUp
    0.50
    guous
    0.50
    ükemmel
    0.49
     grooms
    0.49
    épendance
    0.49
    WithMany
    0.47
    Activations Density 0.004%

    No Known Activations