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. 74518
    Prev
    Next
    INDEX
    Explanations

    Code-related

    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
    ArgsConstructor
    -0.71
    HomeAsUpEnabled
    -0.60
     >=",
    -0.60
     uska
    -0.59
     initComponents
    -0.59
    󠁢
    -0.59
     GSP
    -0.59
     WL
    -0.57
    Formats
    -0.55
     ICD
    -0.54
    POSITIVE LOGITS
     friv
    0.44
    extern
    0.44
    prefixer
    0.43
    Comté
    0.40
    sidemargin
    0.40
    GeneratedCode
    0.40
    掉的
    0.40
     exterior
    0.40
     nakalista
    0.39
    +</
    0.39
    Activations Density 0.032%

    No Known Activations