© 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. 94130
    Prev
    Next
    INDEX
    Explanations

    computer 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
    出版年
    -0.64
     kasarigan
    -0.60
    WebVitals
    -0.59
    ApiModelProperty
    -0.54
    protoimpl
    -0.52
     Waray
    -0.52
     reafon
    -0.52
    SharedDtor
    -0.51
     temprana
    -0.51
     Nok
    -0.50
    POSITIVE LOGITS
    tux
    0.65
    pekte
    0.56
    fant
    0.56
     resourceCulture
    0.55
    ://$
    0.54
    quini
    0.50
     Fant
    0.50
     snippetHide
    0.50
     بيها
    0.50
    __((
    0.48
    Activations Density 0.006%

    No Known Activations