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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91114
    Prev
    Next
    INDEX
    Explanations

    Variety of text types

    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
    olli
    -2.16
    seteq
    -0.60
     resourceCulture
    -0.59
    PreExecute
    -0.58
    ogaster
    -0.52
    queryInterface
    -0.51
    __))
    -0.49
    Stack
    -0.49
    %)$
    -0.48
    SYNOPSIS
    -0.47
    POSITIVE LOGITS
    aarrggbb
    0.67
     Alton
    0.63
    addContainerGap
    0.60
     Thio
    0.59
    новниш
    0.58
    itinéraire
    0.58
    ագրություններ
    0.58
    elemField
    0.57
    ِّف
    0.55
     Euri
    0.54
    Activations Density 1.720%

    No Known Activations