© 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. 5-CLT-HP
    7. 91892
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
    DoubleQuotes
    -0.73
     utafitiHapana
    -0.58
     للمعارف
    -0.58
     sauvages
    -0.52
     veck
    -0.49
     arbetar
    -0.48
     varandra
    -0.48
     nakalista
    -0.48
    IVEREF
    -0.47
     douce
    -0.47
    POSITIVE LOGITS
    WebServlet
    0.85
    السكان
    0.66
     aren
    0.56
    vician
    0.55
    بوابة
    0.54
     overly
    0.53
    ENTIALS
    0.53
    igurumi
    0.52
     nonatomic
    0.52
    MIDDLEWARE
    0.52
    Activations Density 0.000%

    No Known Activations