Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74629
    Prev
    Next
    INDEX
    Explanations

    Technical terms

    np_max-act-logits · 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
    JspWriter
    -0.65
     Comm
    -0.56
    voy
    -0.56
    ming
    -0.55
    WithMany
    -0.53
    setVerticalGroup
    -0.53
    emptyList
    -0.52
    ndes
    -0.52
    ening
    -0.51
    cad
    -0.51
    POSITIVE LOGITS
    saraba
    0.63
    Portail
    0.56
    WEBPACK
    0.54
    ted
    0.53
     referenties
    0.50
     bağlantılar
    0.49
    лтемелер
    0.48
    tedt
    0.48
     kte
    0.47
    WithError
    0.46
    Activations Density 0.002%

    No Known Activations