© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 91595
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     Moms
    -0.25
    ressum
    -0.24
     store
    -0.24
    erdo
    -0.22
     vous
    -0.21
    <bos>
    -0.21
    ajevo
    -0.21
    리를
    -0.20
    бран
    -0.20
    Affirmed
    -0.20
    POSITIVE LOGITS
    GEBURTSDATUM
    1.01
    mybatisplus
    0.84
    windowFixed
    0.83
    AddTagHelper
    0.82
    URLException
    0.77
    ChildScrollView
    0.76
     @"/
    0.76
     marié
    0.76
    MessageTagHelper
    0.74
     TestBed
    0.73
    Activations Density 0.002%

    No Known Activations