© 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. 0-CLT-HP
    7. 42842
    Prev
    Next
    INDEX
    Explanations

    life

    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
     Therefore
    -0.65
     therefore
    -0.65
    Therefore
    -0.63
     donc
    -0.59
     daher
    -0.56
     quindi
    -0.52
     a
    -0.51
    oboda
    -0.49
    ov
    -0.48
     those
    -0.47
    POSITIVE LOGITS
    цездатний
    0.73
    MLLoader
    0.70
     вікі
    0.68
     BoxFit
    0.68
     للاسماء
    0.68
    JsonInclude
    0.66
    Према
    0.66
    UrlResolution
    0.65
     Alen
    0.63
    \{\\
    0.63
    Activations Density 1.663%

    No Known Activations