© 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. 72205
    Prev
    Next
    INDEX
    Explanations

    "U" words

    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
     MainAxisSize
    -0.98
     ModelExpression
    -0.79
     doInBackground
    -0.73
    esModule
    -0.69
    Personendaten
    -0.65
    SharedDtor
    -0.64
    eleste
    -0.57
     BoxFit
    -0.57
     Meksiku
    -0.57
    GenerationType
    -0.56
    POSITIVE LOGITS
     U
    0.70
    UB
    0.63
    U
    0.59
     u
    0.56
     υ
    0.56
     $\
    0.55
    UD
    0.53
    UC
    0.52
    ub
    0.52
    uco
    0.51
    Activations Density 0.011%

    No Known Activations