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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12648
    Prev
    Next
    INDEX
    Explanations

    XML code

    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
    arate
    -0.88
    idential
    -0.62
     curls
    -0.60
    SuspendLayout
    -0.55
     boneless
    -0.54
    __(/*!
    -0.54
    Види
    -0.52
     viv
    -0.49
     bon
    -0.49
    aranja
    -0.47
    POSITIVE LOGITS
    EndGlobalSection
    0.67
    BASEPATH
    0.64
    ButterKnife
    0.63
    IntoConstraints
    0.62
     مرئيه
    0.61
     Baillargeon
    0.58
    zzleHttp
    0.57
     dévelo
    0.56
    cetype
    0.55
    Referanser
    0.55
    Activations Density 0.072%

    No Known Activations