© 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. 93688
    Prev
    Next
    INDEX
    Explanations

    business executives

    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
    :]:
    -0.70
    ativement
    -0.69
    /*---
    -0.68
     invokingState
    -0.67
     ['./
    -0.66
    SequentialGroup
    -0.65
     nakalista
    -0.64
    RenderAtEndOf
    -0.63
     }}"></
    -0.63
     /\.
    -0.62
    POSITIVE LOGITS
     of
    0.43
     chief
    0.36
     alumni
    0.35
    Referanser
    0.35
    DataSnapshot
    0.34
     procurer
    0.34
    BufferException
    0.34
     دیکھیے
    0.33
    קישורים
    0.32
     oncology
    0.32
    Activations Density 0.011%

    No Known Activations