© 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. 40669
    Prev
    Next
    INDEX
    Explanations

    technical/legal contexts

    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
    ches
    -1.83
    CHES
    -1.06
    SharedDtor
    -0.92
    che
    -0.90
     behalf
    -0.86
     estekak
    -0.83
    RTDA
    -0.77
    BeginContext
    -0.75
     nahilalakip
    -0.73
     referenties
    -0.72
    POSITIVE LOGITS
     of
    0.51
    MultipartFile
    0.49
    rxjs
    0.44
     Criterion
    0.44
     Crit
    0.43
     Clar
    0.42
     Klu
    0.42
     Cru
    0.41
    setVerticalGroup
    0.41
    rcl
    0.41
    Activations Density 0.064%

    No Known Activations