© 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. 5-CLT-HP
    7. 687
    Prev
    Next
    INDEX
    Explanations

    decreasing/calming

    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
     يتيمه
    -0.81
    Tikang
    -0.56
    SuspendLayout
    -0.53
     sanitaires
    -0.52
     présidenti
    -0.52
     supprim
    -0.51
     stroom
    -0.50
     natten
    -0.50
     réguli
    -0.48
    BarStyle
    -0.48
    POSITIVE LOGITS
     the
    1.00
    enumi
    0.73
     that
    0.61
     any
    0.60
     your
    0.60
     those
    0.56
     our
    0.54
    atively
    0.52
    })}\
    0.51
     this
    0.50
    Activations Density 0.003%

    No Known Activations