© 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. 1-CLT-HP
    4. 11928
    Prev
    Next
    INDEX
    Explanations

    central

    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
    IntoConstraints
    -0.77
    SequentialGroup
    -0.63
    ########.
    -0.61
     Efq
    -0.59
    kloped
    -0.57
    awtextra
    -0.57
    onViewCreated
    -0.57
    脚注の使い方
    -0.56
    RenderAtEndOf
    -0.55
    principalColumn
    -0.52
    POSITIVE LOGITS
    ViewFeatures
    0.49
    ing
    0.48
    спользу
    0.48
     beginnetje
    0.47
     rij
    0.47
    ening
    0.45
    izing
    0.45
    volving
    0.44
    ian
    0.44
     çar
    0.44
    Activations Density 0.001%

    No Known Activations