© 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. 76844
    Prev
    Next
    INDEX
    Explanations

    investigating

    np_max-act-logits · 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
    脚注の使い方
    -0.51
    RUnlock
    -0.50
     createSlice
    -0.49
     Deal
    -0.48
     Osw
    -0.45
    gonic
    -0.45
    ovka
    -0.44
     Bourg
    -0.44
    cí
    -0.44
    rfloor
    -0.43
    POSITIVE LOGITS
     exploring
    0.98
     considering
    0.94
     explore
    0.86
     examining
    0.85
     investigating
    0.85
     weighing
    0.82
    considering
    0.80
     evaluating
    0.80
     Explore
    0.79
     m
    0.78
    Activations Density 0.001%

    No Known Activations