© 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. 93517
    Prev
    Next
    INDEX
    Explanations

    Questions/inquiries

    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
    way
    -0.54
    .
    -0.48
    ways
    -0.47
    mer
    -0.46
     way
    -0.46
    kan
    -0.43
    say
    -0.41
    if
    -0.41
    ;
    -0.40
    -
    -0.40
    POSITIVE LOGITS
    ьаж
    0.90
    Jereo
    0.87
    DockStyle
    0.81
    Sucesor
    0.80
     CreateTagHelper
    0.78
    igshid
    0.77
     незавершена
    0.76
    LookAnd
    0.75
    Hauptartikel
    0.75
     ProtoMessage
    0.73
    Activations Density 0.001%

    No Known Activations