© 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. 20-CLT-HP
    7. 73673
    Prev
    Next
    INDEX
    Explanations

    things

    np_max-act-logits · 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
     disambiguazione
    -0.75
    脚注の使い方
    -0.72
    DockStyle
    -0.68
    TintMode
    -0.63
    ftagPool
    -0.63
    يكب
    -0.62
     мәкал
    -0.60
     pulumi
    -0.60
    govine
    -0.60
    enumii
    -0.59
    POSITIVE LOGITS
     things
    2.09
    Things
    1.55
     Things
    1.48
    things
    1.45
     THINGS
    1.41
     cosas
    1.37
     coisas
    1.25
     such
    1.20
     choses
    1.19
     Dinge
    1.15
    Activations Density 0.000%

    No Known Activations