© 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. 0-CLT-HP
    7. 42493
    Prev
    Next
    INDEX
    Explanations

    ipot

    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
     Oswald
    -1.24
    rosh
    -1.15
     GenerationType
    -0.73
    Lähteet
    -0.65
     intptr
    -0.62
     HttpNotFound
    -0.61
     незавершена
    -0.58
     Inscrivez
    -0.56
     iprot
    -0.55
    mobileqq
    -0.55
    POSITIVE LOGITS
    isticated
    0.52
     bø
    0.47
    dp
    0.46
    пет
    0.45
    df
    0.44
    uscitation
    0.44
    dH
    0.44
    checkout
    0.44
    ulte
    0.43
    yscale
    0.43
    Activations Density 0.185%

    No Known Activations