© 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. 4-CLT-HP
    7. 866
    Prev
    Next
    INDEX
    Explanations

    two

    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
    ViewFeatures
    -0.53
    bezpe
    -0.52
     ExecuteAsync
    -0.52
    FormTagHelper
    -0.50
    كويكب
    -0.49
    side
    -0.49
    BeginInit
    -0.47
    Post
    -0.47
    ليل
    -0.47
    homonymie
    -0.46
    POSITIVE LOGITS
    moveToFirst
    0.57
     BorderRadius
    0.56
    addGap
    0.54
     redistribute
    0.52
    blau
    0.49
    findpost
    0.48
    ync
    0.48
    iestety
    0.47
    ArgsConstructor
    0.47
     ContentValues
    0.47
    Activations Density 0.001%

    No Known Activations