© 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. 5-CLT-HP
    7. 4831
    Prev
    Next
    INDEX
    Explanations

    itt

    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
    forChild
    -0.66
    AndEndTag
    -0.64
     Ups
    -0.62
    UnusedPrivate
    -0.61
     насељу
    -0.60
     Topping
    -0.60
    complexContent
    -0.58
     brackets
    -0.57
    Sy
    -0.57
    ísticas
    -0.57
    POSITIVE LOGITS
     متعلقه
    0.52
    ance
    0.52
    ances
    0.48
    usammen
    0.40
     ää
    0.39
     sanitarios
    0.39
     myö
    0.37
    ors
    0.36
    ankar
    0.35
    Lähde
    0.35
    Activations Density 0.001%

    No Known Activations