© 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. 0-CLT-HP
    7. 92740
    Prev
    Next
    INDEX
    Explanations

    text

    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
    Personensuche
    -0.75
    posedge
    -0.66
    AutoScaleMode
    -0.65
    RenderAtEndOf
    -0.63
    RegressionTest
    -0.63
     Chwiliwch
    -0.59
    setVerticalGroup
    -0.58
    Hozzáférés
    -0.58
    براير
    -0.54
    …~
    -0.53
    POSITIVE LOGITS
     strings
    0.59
    strings
    0.54
    string
    0.51
     string
    0.50
    SPATH
    0.49
     onlyOwner
    0.49
    let
    0.48
    tur
    0.48
     approximation
    0.47
     gyrus
    0.47
    Activations Density 0.216%

    No Known Activations