© 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. 77800
    Prev
    Next
    INDEX
    Explanations

    transition words

    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
    Though
    -0.78
     Though
    -0.72
     moindre
    -0.71
     précédents
    -0.71
     stället
    -0.69
    another
    -0.69
     prochaines
    -0.66
     automatiques
    -0.65
    paravant
    -0.65
    Another
    -0.65
    POSITIVE LOGITS
     however
    1.55
    however
    0.76
     meanwhile
    0.69
     moreover
    0.67
     однако
    0.67
     jednak
    0.66
    TagMode
    0.65
     therefore
    0.64
     respectively
    0.63
     However
    0.62
    Activations Density 0.000%

    No Known Activations