© 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. 4443
    Prev
    Next
    INDEX
    Explanations

    license

    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
    AndEndTag
    -0.68
    fjspx
    -0.59
    titleMargin
    -0.57
     saites
    -0.56
    uteri
    -0.56
     useAppContext
    -0.54
     CreateTagHelper
    -0.53
     washes
    -0.53
    errHandler
    -0.53
    pulo
    -0.52
    POSITIVE LOGITS
    ENDA
    0.54
    BeginContext
    0.53
    ITECH
    0.50
     kaynağından
    0.47
    enumi
    0.47
    henge
    0.46
    vend
    0.46
    mar
    0.46
    tore
    0.45
    cture
    0.44
    Activations Density 0.014%

    No Known Activations