© 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. 96588
    Prev
    Next
    INDEX
    Explanations

    time

    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
    IContainer
    -0.44
    onLoad
    -0.43
    oner
    -0.42
     abbastanza
    -0.41
     necessità
    -0.40
    lakukan
    -0.40
     posto
    -0.40
    he
    -0.39
    阔
    -0.39
    ie
    -0.38
    POSITIVE LOGITS
    Parcelize
    0.81
    GEBURTSDATUM
    0.75
     propOrder
    0.74
    ingtones
    0.71
     actionMode
    0.69
    uarts
    0.66
     autorytatywna
    0.66
    setVerticalGroup
    0.65
     setting
    0.64
    RuleContext
    0.63
    Activations Density 0.001%

    No Known Activations