© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91843
    Prev
    Next
    INDEX
    Explanations

    practice

    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
    zeiti
    -0.52
    hasOwnProperty
    -0.40
    从
    -0.38
     Offisielt
    -0.37
     respectivas
    -0.37
     bulunur
    -0.36
    CRIP
    -0.35
    izoen
    -0.35
    <h1>
    -0.35
    getOriginal
    -0.35
    POSITIVE LOGITS
    +#+#
    0.82
     CreateTagHelper
    0.77
     الدولى
    0.67
    brigens
    0.66
    קישורים
    0.65
     nakalista
    0.65
    anyahu
    0.64
     kasarigan
    0.64
    ILayout
    0.63
     فريبيس
    0.63
    Activations Density 0.004%

    No Known Activations