© 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. 4-CLT-HP
    7. 952
    Prev
    Next
    INDEX
    Explanations

    Repetitive movement or thought

    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
    twimg
    -0.70
    Hentet
    -0.62
    GEBURTSDATUM
    -0.60
     pulumi
    -0.56
    webElement
    -0.55
     valour
    -0.55
     Templeton
    -0.54
    )}_
    -0.54
    ERAL
    -0.53
     adjournment
    -0.53
    POSITIVE LOGITS
     of
    0.81
     things
    0.74
     thing
    0.65
    things
    0.60
    Things
    0.56
     Things
    0.56
     THINGS
    0.53
     Roskov
    0.52
    thing
    0.52
     rzeczy
    0.50
    Activations Density 0.008%

    No Known Activations