© 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. 72676
    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
     المعيارى
    -0.82
     betweenstory
    -0.65
    depth
    -0.63
     समीक्षाओं
    -0.60
    ็จ
    -0.60
    efois
    -0.60
    MEDIUM
    -0.60
    BULL
    -0.60
    ніципалі
    -0.59
    avyzd
    -0.59
    POSITIVE LOGITS
     Dr
    0.60
    Dr
    0.54
     dr
    0.44
    dr
    0.42
     Doctor
    0.40
     []:
    0.33
     DIEGO
    0.32
     डॉ
    0.31
    المناصب
    0.31
    latform
    0.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.