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. 0-CLT-HP
    4. 44689
    Prev
    Next
    INDEX
    Explanations

    one

    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
     one
    -1.18
    one
    -0.73
     ones
    -0.65
     Monfieur
    -0.63
     uno
    -0.58
     один
    -0.57
     unul
    -0.56
     één
    -0.56
    One
    -0.54
     Eſ
    -0.54
    POSITIVE LOGITS
     of
    0.92
    الحياه
    0.81
    EndGlobalSection
    0.79
     nakalista
    0.75
    исленность
    0.73
    MLLoader
    0.71
    yntaxException
    0.69
    IndentedString
    0.68
     surla
    0.68
    Personendaten
    0.67
    Activations Density 0.002%

    No Known Activations