© 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. 5-CLT-HP
    7. 95080
    Prev
    Next
    INDEX
    Explanations

    punctuation/numbers

    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
    are
    -0.49
    UniformLocation
    -0.44
     are
    -0.43
     there
    -0.43
     שלו
    -0.43
    co
    -0.42
    ho
    -0.42
     function
    -0.41
     ocas
    -0.41
    Suara
    -0.41
    POSITIVE LOGITS
     وتسجيلات
    0.85
    ]='\
    0.65
     AssemblyCulture
    0.65
    ]--;
    0.64
    ]){
    0.63
    annica
    0.63
     tartalomajánló
    0.62
    الحياه
    0.62
    KommentareTeilen
    0.61
    istoitu
    0.60
    Activations Density 0.003%

    No Known Activations