© 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. 4-CLT-HP
    7. 1287
    Prev
    Next
    INDEX
    Explanations

    ual

    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
    Enllaces
    -0.73
     Normdatei
    -0.62
    DOCTYPE
    -0.62
     naman
    -0.58
     cdti
    -0.56
     Mahi
    -0.54
     Monark
    -0.54
    hoeddwyd
    -0.52
    MOUNT
    -0.52
     drum
    -0.52
    POSITIVE LOGITS
    TOBER
    0.53
    Välislingid
    0.50
    NameInMap
    0.49
    Interpolator
    0.47
    xsi
    0.47
    yntaxException
    0.46
    cinnati
    0.46
     ExecuteAsync
    0.45
    Pyx
    0.45
    Manbalar
    0.45
    Activations Density 0.001%

    No Known Activations