© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92651
    Prev
    Next
    INDEX
    Explanations

    pantheon

    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
    hw
    -0.79
    DeleteBehavior
    -0.69
     unknownFields
    -0.68
     intptr
    -0.64
     Roskov
    -0.64
    twimg
    -0.60
     TestBed
    -0.59
    AutoScaleMode
    -0.59
    LEncoder
    -0.59
     ProtoMessage
    -0.59
    POSITIVE LOGITS
    Inc
    0.53
     produisons
    0.52
     automatiques
    0.51
     jäsen
    0.51
    try
    0.50
    hoeddwyd
    0.49
     saites
    0.46
    rial
    0.45
    UserScript
    0.45
     näh
    0.45
    Activations Density 0.075%

    No Known Activations