© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4434
    Prev
    Next
    INDEX
    Explanations

    coding/grammar/punctuation

    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
     shares
    -0.47
     profondità
    -0.46
     herself
    -0.45
     BrowserModule
    -0.45
    UrlResolution
    -0.45
     оригіналу
    -0.44
    virons
    -0.44
    otri
    -0.43
     tratti
    -0.43
     laborales
    -0.42
    POSITIVE LOGITS
     typelib
    0.74
     Audiodateien
    0.69
    IUrlHelper
    0.61
     kasarigan
    0.59
     able
    0.57
    Diweddarwch
    0.56
     intptr
    0.56
     دیکھیے
    0.56
     excellent
    0.54
    jestic
    0.54
    Activations Density 0.000%

    No Known Activations