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. 73850
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
     disc
    -0.42
    Kariera
    -0.42
    дже
    -0.41
    ism
    -0.40
    be
    -0.40
    SM
    -0.39
    는데
    -0.39
    ino
    -0.39
    пия
    -0.38
    led
    -0.38
    POSITIVE LOGITS
    onAttach
    0.77
    StoryboardSegue
    0.73
     GetEnumerator
    0.73
     enfans
    0.71
    HtmlAttribute
    0.69
     ſind
    0.68
     Theſe
    0.66
     PhpStorm
    0.66
     ſy
    0.66
    tagHelper
    0.65
    Activations Density 0.000%

    No Known Activations