© 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. 76720
    Prev
    Next
    INDEX
    Explanations

    configuration files

    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
     tartalomajánló
    -0.62
    twimg
    -0.58
     mourut
    -0.57
     tuong
    -0.54
    guenos
    -0.53
     wußte
    -0.53
     vägen
    -0.52
    Попис
    -0.51
     gjø
    -0.51
     européennes
    -0.51
    POSITIVE LOGITS
     sight
    0.70
     hart
    0.59
    POSURE
    0.58
     hand
    0.57
     large
    0.54
     heart
    0.53
    GraphicsUnit
    0.53
    InstanceState
    0.53
     للمعارف
    0.53
     hands
    0.52
    Activations Density 0.001%

    No Known Activations