© 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. 1-CLT-HP
    7. 15438
    Prev
    Next
    INDEX
    Explanations

    product manufacturing and sales

    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
    ReusableCell
    -0.75
     princí
    -0.55
    contentLoaded
    -0.54
     sécher
    -0.54
     adultes
    -0.53
    Aholisi
    -0.52
     förm
    -0.52
    adpleegd
    -0.51
    ziehen
    -0.50
     médaille
    -0.50
    POSITIVE LOGITS
    Portale
    0.63
    AnimationsModule
    0.47
    Kanpo
    0.46
    __((
    0.43
    IntoConstraints
    0.43
    eachtet
    0.42
     VCR
    0.42
    iedene
    0.41
     Sonos
    0.41
    rager
    0.41
    Activations Density 0.032%

    No Known Activations