© 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. 94171
    Prev
    Next
    INDEX
    Explanations

    speaking

    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
     Efq
    -1.15
     itſelf
    -1.11
     myſelf
    -1.05
     Theſe
    -1.03
     étoit
    -1.01
     feroit
    -1.00
     auroit
    -0.96
     avoient
    -0.95
     pouvoit
    -0.94
     Majefty
    -0.90
    POSITIVE LOGITS
    .
    0.70
     
    0.69
    s
    0.65
     of
    0.61
     I
    0.60
     N
    0.58
     (
    0.57
     R
    0.54
     G
    0.54
    ,
    0.53
    Activations Density 0.028%

    No Known Activations