© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93583
    Prev
    Next
    INDEX
    Explanations

    services and opportunities

    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
     مرئيه
    -0.85
    BeginContext
    -0.69
    uxxxx
    -0.68
     ویکی‌پدی
    -0.67
    <bos>
    -0.65
     виправивши
    -0.62
    DockStyle
    -0.61
    Portale
    -0.61
     poveznice
    -0.61
     tendered
    -0.60
    POSITIVE LOGITS
     cover
    0.58
     can
    0.53
     Gewähr
    0.52
     run
    0.50
     come
    0.50
     do
    0.50
     hold
    0.49
     include
    0.49
     ongles
    0.46
     simplify
    0.46
    Activations Density 0.014%

    No Known Activations