© 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. 5-CLT-HP
    7. 93114
    Prev
    Next
    INDEX
    Explanations

    around

    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
    Skocz
    -0.50
    ènements
    -0.49
    adaptiveStyles
    -0.48
     dislocations
    -0.47
     VIDEOTAPE
    -0.46
    assertRaises
    -0.45
     lags
    -0.44
     nakalista
    -0.44
    MockMvc
    -0.44
     bacter
    -0.43
    POSITIVE LOGITS
     them
    0.73
    them
    0.65
     themselves
    0.61
     THEM
    0.59
     travailleurs
    0.57
     the
    0.56
     eux
    0.54
    TagMode
    0.53
     enfans
    0.52
     AssemblyTitle
    0.52
    Activations Density 0.006%

    No Known Activations