© 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. 0-CLT-HP
    7. 42226
    Prev
    Next
    INDEX
    Explanations

    judgements

    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
    ThroughAttribute
    -0.71
     UITableViewCell
    -0.56
    EditorBrowsable
    -0.53
     assertion
    -0.52
     judgment
    -0.49
     guidance
    -0.47
     choice
    -0.46
     designation
    -0.46
     judgement
    -0.45
     creation
    -0.45
    POSITIVE LOGITS
     Baillargeon
    0.65
    Aktualisiert
    0.63
    ścioła
    0.57
    Diwedd
    0.55
    ostom
    0.54
    DECREF
    0.54
     effected
    0.54
     doInBackground
    0.54
    Życiorys
    0.52
    Handlung
    0.52
    Activations Density 0.038%

    No Known Activations