© 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. 4983
    Prev
    Next
    INDEX
    Explanations

    Actions being redone

    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
     of
    -0.80
     were
    -0.41
    of
    -0.41
     Protobuf
    -0.38
     opcional
    -0.37
     bank
    -0.36
     took
    -0.35
     sf
    -0.35
    っこう
    -0.35
    astéro
    -0.35
    POSITIVE LOGITS
     the
    1.04
    webElementXpaths
    1.00
    TagMode
    0.82
    LookAnd
    0.81
    évaluateur
    0.75
    posedge
    0.74
     AssemblyCulture
    0.70
    تقاوى
    0.70
     تانيه
    0.69
     it
    0.68
    Activations Density 0.004%

    No Known Activations