© 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. 97643
    Prev
    Next
    INDEX
    Explanations

    our

    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
    CreateModel
    -0.52
    chriften
    -0.47
    toMatchSnapshot
    -0.47
    transQ
    -0.47
     JUGA
    -0.46
    umah
    -0.46
    υμ
    -0.45
     Italijani
    -0.45
    prepareStatement
    -0.45
     насељу
    -0.45
    POSITIVE LOGITS
     were
    0.85
     tried
    0.72
     studied
    0.72
    were
    0.72
     last
    0.69
     discovered
    0.68
     needed
    0.67
     sought
    0.64
     doubted
    0.63
     reviewed
    0.63
    Activations Density 0.001%

    No Known Activations