© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92657
    Prev
    Next
    INDEX
    Explanations

    detecting

    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
    ethene
    -0.59
    ⓧ
    -0.58
     interchangeably
    -0.57
    Vidite
    -0.56
     poveznice
    -0.55
     capaces
    -0.52
    Havolalar
    -0.52
     breaker
    -0.51
     esternos
    -0.51
     faltar
    -0.51
    POSITIVE LOGITS
     the
    0.86
     a
    0.66
     our
    0.66
     important
    0.64
     some
    0.63
     two
    0.63
     several
    0.59
     all
    0.56
     your
    0.56
     various
    0.55
    Activations Density 0.061%

    No Known Activations