© 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. 4-CLT-HP
    7. 508
    Prev
    Next
    INDEX
    Explanations

    organization, business

    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
     defaultstate
    -0.61
     betweenstory
    -0.59
    protoimpl
    -0.58
     дописавши
    -0.57
     autorytatywna
    -0.57
     nakalista
    -0.56
     coarser
    -0.55
     octaves
    -0.55
    dengar
    -0.55
    ConstraintMaker
    -0.55
    POSITIVE LOGITS
     Promotes
    0.58
     Has
    0.57
     promotes
    0.54
    EMPL
    0.54
    Supports
    0.54
     Cont
    0.52
     Will
    0.51
     Supports
    0.51
     Emphas
    0.50
     Enables
    0.49
    Activations Density 0.005%

    No Known Activations