© 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. 91727
    Prev
    Next
    INDEX
    Explanations

    code

    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
    GenerationType
    -0.93
    IContainer
    -0.78
    Vidite
    -0.76
    ^(@)
    -0.71
    StoreMessageInfo
    -0.71
    webElementXpaths
    -0.71
    isContained
    -0.66
     دیکھیے
    -0.66
     Majefty
    -0.65
    </caption>
    -0.65
    POSITIVE LOGITS
    mar
    0.55
    4
    0.54
    ite
    0.54
     Mar
    0.52
    7
    0.49
    9
    0.49
    5
    0.48
    gre
    0.48
    Mar
    0.48
    8
    0.48
    Activations Density 0.001%

    No Known Activations