© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2652
    Prev
    Next
    INDEX
    Explanations

    World. It is too difficult to discern a specific shared theme

    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
    BeginContext
    -0.79
    DispatchToProps
    -0.79
    AutoScaleMode
    -0.75
     ویکی‌پدیا
    -0.75
    ImageContext
    -0.75
    Personendaten
    -0.70
     nahilalakip
    -0.68
    hoeddwyd
    -0.67
     BoxFit
    -0.65
    ⓧ
    -0.61
    POSITIVE LOGITS
    maakt
    0.46
    mappedBy
    0.46
    preventDefault
    0.43
    achet
    0.43
     ator
    0.42
     betweenstory
    0.42
     manufact
    0.42
     Aval
    0.40
     swear
    0.39
    Variables
    0.39
    Activations Density 0.003%

    No Known Activations