© 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. 0-CLT-HP
    7. 93185
    Prev
    Next
    INDEX
    Explanations

    tas

    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
    (!__
    -0.59
    ropractic
    -0.56
    StreetMap
    -0.54
    ipto
    -0.54
     tas
    -0.53
    rylic
    -0.52
     arbitration
    -0.52
    vection
    -0.52
    ttino
    -0.52
     compounded
    -0.51
    POSITIVE LOGITS
     nôtre
    0.59
    RenderAtEndOf
    0.56
    actéristique
    0.52
     illustrazione
    0.51
     Australie
    0.51
    InputBorder
    0.50
     betweenstory
    0.48
    falt
    0.48
     colpa
    0.48
     vœux
    0.47
    Activations Density 0.223%

    No Known Activations