© 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. 1-CLT-HP
    7. 14960
    Prev
    Next
    INDEX
    Explanations

    Ka

    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
    enumi
    -0.76
     hjemme
    -0.67
    initializer
    -0.63
    hoots
    -0.63
     locaux
    -0.57
     lika
    -0.56
    ScopeManager
    -0.56
    bootstrapcdn
    -0.55
     littéraire
    -0.54
     proposito
    -0.53
    POSITIVE LOGITS
    Попис
    0.62
    CONSIN
    0.60
    xFFFFFFFF
    0.57
    Personensuche
    0.56
    ToTensor
    0.55
     finger
    0.54
    gettime
    0.52
     requestCode
    0.52
    الإنجليزية
    0.52
     nakalista
    0.52
    Activations Density 0.018%

    No Known Activations