© 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. 72519
    Prev
    Next
    INDEX
    Explanations

    programming and code

    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
    Soorten
    -0.49
    yty
    -0.48
    INAS
    -0.48
     trajets
    -0.47
    getDoctrine
    -0.47
    FunctionFlags
    -0.47
    Eks
    -0.47
    thenes
    -0.46
     erin
    -0.46
    sampler
    -0.46
    POSITIVE LOGITS
     lie
    0.93
     LIE
    0.77
     Lie
    0.70
    Lie
    0.64
     Breakout
    0.64
     Break
    0.62
    Break
    0.62
    break
    0.59
     BREAK
    0.58
    ürlich
    0.57
    Activations Density 0.000%

    No Known Activations