© 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. 20-CLT-HP
    7. 75423
    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
     requestCode
    -0.58
     Roses
    -0.58
     Signalez
    -0.56
    Dislikes
    -0.56
     Gazette
    -0.54
    ్రామ
    -0.53
    ритори
    -0.53
     roses
    -0.53
    клопе
    -0.52
    SequentialGroup
    -0.52
    POSITIVE LOGITS
     mergeFrom
    0.65
     fabric
    0.57
     align
    0.55
    ffindor
    0.53
     commission
    0.51
    TestBed
    0.49
     MainAxisSize
    0.49
    vesti
    0.48
     alig
    0.48
    commission
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.