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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94038
    Prev
    Next
    INDEX
    Explanations

    web page snippets

    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
    setVerticalGroup
    -0.70
    AutoScaleMode
    -0.68
    TypedDataSet
    -0.66
     gehad
    -0.63
    LookAnd
    -0.62
    AndEndTag
    -0.60
    CppMethod
    -0.56
     hemma
    -0.56
     mijne
    -0.55
     mergeFrom
    -0.55
    POSITIVE LOGITS
    unner
    0.47
    ╝
    0.46
     الفلك
    0.43
     Komisi
    0.41
     benefit
    0.41
     ren
    0.40
     Author
    0.40
     nul
    0.40
     story
    0.40
     date
    0.40
    Activations Density 0.006%

    No Known Activations