© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1875
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ResumeLayout
    -0.58
    AlterField
    -0.57
    FunctionFlags
    -0.53
     Credo
    -0.52
     plunger
    -0.50
     IntPtr
    -0.50
    TextAppearance
    -0.49
     Präsidenten
    -0.49
     Wikimedijinoj
    -0.49
    classnames
    -0.48
    POSITIVE LOGITS
     تانيه
    0.89
    orgon
    0.61
     ujednoznacz
    0.57
     Palme
    0.56
     uLocal
    0.55
    MOV
    0.54
     requestCode
    0.53
     Coron
    0.53
     sats
    0.53
     abon
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.