© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38325
    Prev
    Next
    INDEX
    Explanations

    Suffixes like -ize, -ious

    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
    iz
    -0.94
    izable
    -0.81
    whip
    -0.70
    IZ
    -0.69
     whip
    -0.64
    izzy
    -0.64
    __*/
    -0.63
     WebDriverWait
    -0.63
     whips
    -0.61
    omas
    -0.60
    POSITIVE LOGITS
    netbeans
    0.52
    canActivate
    0.52
    gsub
    0.47
     essencial
    0.47
     ModelRenderer
    0.46
    cives
    0.46
    ocino
    0.46
     Fabulous
    0.44
    glTranslatef
    0.44
    Дере
    0.43
    Activations Density 0.124%

    No Known Activations