© 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. 42537
    Prev
    Next
    INDEX
    Explanations

    exponentially/optimally

    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
     itſelf
    -1.14
     Monfieur
    -1.01
    脚注の使い方
    -0.99
     pleaſure
    -0.99
     Jefus
    -0.98
     Anſ
    -0.97
     himſelf
    -0.97
    TagMode
    -0.94
     beſt
    -0.92
     myſelf
    -0.90
    POSITIVE LOGITS
     reg
    0.54
     car
    0.54
     media
    0.53
     Car
    0.52
     des
    0.50
     virtual
    0.50
     an
    0.49
    bige
    0.49
     O
    0.48
     berke
    0.48
    Activations Density 0.089%

    No Known Activations