© 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. 76951
    Prev
    Next
    INDEX
    Explanations

    Code, urls, special chars

    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
    DoubleQuotes
    -0.48
    MethodManager
    -0.42
     ब्रेकडाउन
    -0.39
    #__
    -0.35
     PeEnEo
    -0.35
    Bibliografie
    -0.35
     Schulze
    -0.34
    InSection
    -0.33
    chaik
    -0.33
    NoError
    -0.32
    POSITIVE LOGITS
     pandémie
    0.65
    oa̍t
    0.62
    fjspx
    0.60
     HasFactory
    0.58
    canestro
    0.58
    fhir
    0.57
     ContentValues
    0.57
    PLIES
    0.57
    gya
    0.57
     biology
    0.56
    Activations Density 0.000%

    No Known Activations