© 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. 76745
    Prev
    Next
    INDEX
    Explanations

    HTML and code, generally

    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
    出版年
    -0.69
     transfieras
    -0.69
    djangoproject
    -0.67
    SharedCtor
    -0.65
    featureID
    -0.65
    adaptiveStyles
    -0.64
    tanleria
    -0.61
    UnknownFieldSet
    -0.60
    principalColumn
    -0.59
    
    -0.59
    POSITIVE LOGITS
    álen
    0.53
     pit
    0.50
    Kamp
    0.46
    Filmographie
    0.46
     otomatig
    0.46
     pitt
    0.45
    toBe
    0.45
     CAMP
    0.44
     Combien
    0.43
    Xl
    0.43
    Activations Density 0.001%

    No Known Activations