© 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. 0-CLT-HP
    4. 43839
    Prev
    Next
    INDEX
    Explanations

    two

    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
    何より
    -0.56
     serta
    -0.54
    agi
    -0.50
    <bos>
    -0.47
    かつ
    -0.47
     ruedas
    -0.47
    াব
    -0.47
    OGRAPH
    -0.46
    andi
    -0.45
    andis
    -0.45
    POSITIVE LOGITS
     Efq
    0.99
     snippetHide
    0.78
     Majefty
    0.75
     ModelExpression
    0.74
     Monfieur
    0.74
     chofe
    0.74
     houſe
    0.73
     poffible
    0.69
     themſelves
    0.69
     mergeFrom
    0.68
    Activations Density 0.117%

    No Known Activations