© 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. 4-CLT-HP
    7. 2172
    Prev
    Next
    INDEX
    Explanations

    class

    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
     snippetHide
    -0.76
     Theſe
    -0.66
     reaſon
    -0.59
    queryInterface
    -0.56
     idem
    -0.55
     purpoſe
    -0.55
     ſeveral
    -0.54
     ſame
    -0.54
    ivably
    -0.54
     myſelf
    -0.54
    POSITIVE LOGITS
    WebElementEntity
    0.56
    LookAnd
    0.52
    has
    0.51
    principalColumn
    0.51
    6
    0.50
    hasiswa
    0.48
    >{@
    0.48
     sogget
    0.47
    OGND
    0.47
     onCreateView
    0.46
    Activations Density 0.016%

    No Known Activations