© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97663
    Prev
    Next
    INDEX
    Explanations

    Acronyms and abbreviations

    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
     nahilalakip
    -0.65
    webElementXpaths
    -0.55
    aw
    -0.45
    wh
    -0.43
    ce
    -0.42
    PT
    -0.41
    source
    -0.41
    RP
    -0.40
    Lw
    -0.40
    Spo
    -0.40
    POSITIVE LOGITS
    copg
    0.68
    Становништво
    0.66
    ScopeManager
    0.63
    complexType
    0.62
    quelize
    0.62
    MLLoader
    0.60
    invokeLater
    0.59
    BagConstraints
    0.59
    ResponseWriter
    0.59
    стьян
    0.58
    Activations Density 0.002%

    No Known Activations