© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3386
    Prev
    Next
    INDEX
    Explanations

    Bay

    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
     …
    -0.40
     own
    -0.38
    …
    -0.37
     he
    -0.36
     can
    -0.35
     to
    -0.33
    ’
    -0.32
    ,
    -0.32
     goes
    -0.31
     or
    -0.30
    POSITIVE LOGITS
     للاسماء
    1.27
     CreateTagHelper
    1.20
    SourceChecksum
    1.11
     الحره
    1.10
    LookAnd
    1.07
     defaultstate
    1.05
    Personendaten
    1.05
    ValueStyle
    1.05
    تقاوى
    1.05
    WriteTagHelper
    1.05
    Activations Density 0.029%

    No Known Activations