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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4906
    Prev
    Next
    INDEX
    Explanations

    articles and possessive pronouns

    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
    DoubleQuotes
    -0.72
    之一
    -0.57
    TemporalType
    -0.53
    DataAnnotations
    -0.51
    GOTREF
    -0.50
    atguigu
    -0.50
     مشين
    -0.49
    inquirer
    -0.48
    endpush
    -0.48
    writeFieldEnd
    -0.48
    POSITIVE LOGITS
     насељу
    0.63
    ponses
    0.57
    openzeppelin
    0.56
    Clik
    0.56
    ])):
    0.54
    Aholisi
    0.53
    UserScript
    0.52
     newly
    0.52
    newName
    0.50
     Schild
    0.50
    Activations Density 0.007%

    No Known Activations