© 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. 45609
    Prev
    Next
    INDEX
    Explanations

    conval

    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
    EDA
    -0.64
    aa
    -0.56
    mend
    -0.55
    mHandler
    -0.54
    مثلة
    -0.54
     Comuni
    -0.53
    eda
    -0.52
    ṁ
    -0.52
    Armen
    -0.52
    ṃ
    -0.52
    POSITIVE LOGITS
     виправивши
    0.58
    parsedMessage
    0.58
    jsonwebtoken
    0.57
    Segoe
    0.57
    posób
    0.55
    ipedi
    0.54
    ASKET
    0.53
    ⁩
    0.53
    NameInMap
    0.52
    dafx
    0.52
    Activations Density 0.136%

    No Known Activations