© 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. 43454
    Prev
    Next
    INDEX
    Explanations

    Words ending in "ative"

    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
    ative
    -1.30
    ATIVE
    -1.01
    atively
    -0.74
     internal
    -0.74
     representative
    -0.73
     vnitř
    -0.71
     internos
    -0.70
     wewnętr
    -0.69
     внутрен
    -0.69
    内部
    -0.65
    POSITIVE LOGITS
    posedge
    0.68
     ReactDOM
    0.58
    homonymie
    0.57
     secretaries
    0.57
     alleles
    0.56
    bkz
    0.56
    pageY
    0.56
     Sos
    0.53
     cache
    0.52
     שלי
    0.52
    Activations Density 0.040%

    No Known Activations