© 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. 5-CLT-HP
    7. 94895
    Prev
    Next
    INDEX
    Explanations

    code and scientific text snippets

    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
    yte
    -0.51
    tedly
    -0.49
     T
    -0.48
    toje
    -0.48
     Sa
    -0.48
     C
    -0.47
     Si
    -0.47
     every
    -0.47
     The
    -0.46
    iro
    -0.46
    POSITIVE LOGITS
    évaluateur
    0.75
    ThroughAttribute
    0.74
     disambiguazione
    0.73
    Autoritní
    0.70
     ujednoznacz
    0.66
     Walkover
    0.64
     تانيه
    0.64
     препратки
    0.63
    contentLoaded
    0.63
    Geplaatst
    0.61
    Activations Density 0.001%

    No Known Activations