© 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. 5-CLT-HP
    7. 97208
    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
    __':
    -0.90
    VIAF
    -0.89
     Himo
    -0.83
    __":
    -0.80
    ModelAdmin
    -0.75
     nakalista
    -0.75
    Бахар
    -0.75
    存于互联网档案馆
    -0.75
    SequentialGroup
    -0.73
     numberOfRows
    -0.71
    POSITIVE LOGITS
     palsu
    0.40
     primas
    0.39
     peně
    0.35
     
    0.34
     enkelte
    0.34
     stør
    0.33
    seende
    0.33
     Next
    0.33
     persoalan
    0.33
    槻
    0.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.