Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74312
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    extendable
    -0.71
    hancing
    -0.68
    olding
    -0.68
    activating
    -0.67
    dropping
    -0.66
    kening
    -0.66
    aging
    -0.66
    folding
    -0.65
    viating
    -0.65
    breaking
    -0.64
    POSITIVE LOGITS
     danced
    0.84
     acted
    0.82
     marched
    0.82
     played
    0.81
     sailed
    0.80
     walked
    0.80
     fought
    0.79
     interacted
    0.79
     waited
    0.78
     tasted
    0.78
    Activations Density 0.268%

    No Known Activations