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. 74283
    Prev
    Next
    INDEX
    Explanations

    Source material

    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
    __(/*!
    -0.90
    BeginContext
    -0.73
    rrggbb
    -0.68
    elemField
    -0.67
    HasForeignKey
    -0.65
    AndEndTag
    -0.65
    onOptions
    -0.64
    expandindo
    -0.64
     ***!
    -0.63
     doInBackground
    -0.62
    POSITIVE LOGITS
    gnen
    0.44
    MATERIAL
    0.42
     materiale
    0.41
    LETIN
    0.41
     material
    0.40
    FactoryBean
    0.39
    Material
    0.39
    Unmarshaller
    0.39
     Walkover
    0.39
    material
    0.38
    Activations Density 0.015%

    No Known Activations