© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73110
    Prev
    Next
    INDEX
    Explanations

    Code and copyrights

    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
     ModelExpression
    -0.56
     CreateTagHelper
    -0.47
    :+:
    -0.45
    ilai
    -0.44
     AspNetCore
    -0.41
    abestanden
    -0.41
    Gweler
    -0.41
    </>
    -0.39
    imeter
    -0.38
     Paglinawan
    -0.38
    POSITIVE LOGITS
    LookAnd
    0.74
    RegistryLite
    0.64
    ésultat
    0.60
     Inv
    0.59
     elect
    0.59
    جیب
    0.59
     handcuffs
    0.58
    طقة
    0.57
    Ris
    0.55
    Autoritní
    0.54
    Activations Density 0.001%

    No Known Activations