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. 20-CLT-HP
    4. 74419
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
    <eos>
    -0.40
     hvert
    -0.37
    XmlRootElement
    -0.36
    fated
    -0.36
     Extended
    -0.32
     Emerging
    -0.32
     prochains
    -0.32
    ...
    -0.31
    Extended
    -0.31
    De
    -0.31
    POSITIVE LOGITS
     صوتيه
    0.85
    ſelf
    0.79
    tagHelperRunner
    0.79
     ویکی‌پدیا
    0.75
    MigrationBuilder
    0.74
     myſelf
    0.74
     AssemblyTitle
    0.73
    tones
    0.72
     linkovi
    0.72
    principalTable
    0.71
    Activations Density 0.005%

    No Known Activations