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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91099
    Prev
    Next
    INDEX
    Explanations

    adverbial suffixes

    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
    ately
    -2.67
    ously
    -1.49
    ateness
    -1.27
    tably
    -1.08
    ATELY
    -1.05
    antly
    -1.03
    ely
    -1.01
    tely
    -0.98
    ELY
    -0.89
    aneously
    -0.88
    POSITIVE LOGITS
    mbic
    0.60
    ValueStyle
    0.55
     officinalis
    0.55
    IContainer
    0.51
    jooq
    0.51
     Ours
    0.50
     volunt
    0.49
     genital
    0.48
     administracy
    0.48
    riti
    0.47
    Activations Density 1.553%

    No Known Activations