© 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. 45266
    Prev
    Next
    INDEX
    Explanations

    categorical complicated

    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
     complicated
    -0.85
    GOTREF
    -0.81
    complicated
    -0.77
    simplified
    -0.71
    INGREDIENTES
    -0.67
    culares
    -0.66
     Wikispecies
    -0.65
    __":
    -0.64
    JsonHelper
    -0.63
     SimpleName
    -0.63
    POSITIVE LOGITS
    ofluor
    0.48
    <<<<
    0.45
    架
    0.44
    ּוֹ
    0.44
     uuidv
    0.42
    ladu
    0.42
     worth
    0.41
     major
    0.40
    ्त
    0.40
     "..\..\..\
    0.40
    Activations Density 1.521%

    No Known Activations