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. 73568
    Prev
    Next
    INDEX
    Explanations

    code and technical content

    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
    within
    -0.65
     Within
    -0.63
    Within
    -0.61
     to
    -0.57
     within
    -0.54
    到
    -0.52
     into
    -0.52
    wards
    -0.51
    Somewhere
    -0.50
     назад
    -0.50
    POSITIVE LOGITS
    %");
    0.65
     */;
    0.63
     onData
    0.62
    NUMX
    0.60
    Autoritní
    0.60
    '/',
    0.59
    }}=$
    0.59
    ]]=
    0.59
    :]:
    0.59
    AllAfrica
    0.58
    Activations Density 0.000%

    No Known Activations