© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11398
    Prev
    Next
    INDEX
    Explanations

    tweet

    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
     tweet
    -1.68
     tweeting
    -1.53
     tweets
    -1.49
     Tweet
    -1.48
    tweet
    -1.35
    Tweet
    -1.32
     Tweets
    -1.28
     tweeted
    -1.27
     Twe
    -1.23
     tweeter
    -1.20
    POSITIVE LOGITS
    @[+][
    0.47
    castle
    0.47
    book
    0.46
    ard
    0.46
     mergeFrom
    0.44
    ţion
    0.44
    block
    0.41
    ersen
    0.41
    back
    0.41
     indoor
    0.41
    Activations Density 0.005%

    No Known Activations