© 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. 4903
    Prev
    Next
    INDEX
    Explanations

    code

    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
    virons
    -0.70
    getActiveSheet
    -0.67
    rophoresis
    -0.60
    enumi
    -0.60
    CompleteListener
    -0.59
    åga
    -0.59
    ี้ยง
    -0.59
     estimés
    -0.59
     doInBackground
    -0.56
    lapsingToolbar
    -0.56
    POSITIVE LOGITS
    DoubleQuotes
    0.50
    IBar
    0.49
    $}
    0.47
     alguna
    0.47
     Dada
    0.46
     "..\..\
    0.46
    Strip
    0.44
    Modific
    0.43
    اديم
    0.42
     alguno
    0.41
    Activations Density 0.001%

    No Known Activations