© 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. 1-CLT-HP
    7. 9056
    Prev
    Next
    INDEX
    Explanations

    still

    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
    tagHelperRunner
    -0.73
     myſelf
    -0.72
     ſtill
    -0.70
     quæ
    -0.66
     pyridine
    -0.66
     ſta
    -0.65
    ergies
    -0.65
     kasarigan
    -0.65
     houſe
    -0.65
     lenker
    -0.65
    POSITIVE LOGITS
    postIndex
    0.45
    anse
    0.42
     fakt
    0.41
     considering
    0.41
    เสีย
    0.41
     faktor
    0.41
     Faktor
    0.40
    ναι
    0.40
     gainera
    0.38
    
    0.38
    Activations Density 0.093%

    No Known Activations