© 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. 1-CLT-HP
    7. 14330
    Prev
    Next
    INDEX
    Explanations

    be

    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
     Odysseus
    -0.71
    ngdoc
    -0.65
     AssemblyProduct
    -0.56
     الرياضيه
    -0.56
     Winchester
    -0.55
    Дереккөздер
    -0.52
     combineReducers
    -0.52
    Jährige
    -0.51
    matchCondition
    -0.50
    __':
    -0.47
    POSITIVE LOGITS
     Waray
    0.58
     consultato
    0.52
     []:
    0.52
    Revenge
    0.49
    ViewFeatures
    0.48
    mask
    0.48
    type
    0.48
     vVar
    0.48
    andinav
    0.48
     gawas
    0.48
    Activations Density 0.003%

    No Known Activations