© 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. 9169
    Prev
    Next
    INDEX
    Explanations

    volume

    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
    bkz
    -0.61
    ArrowToggle
    -0.57
    хьтан
    -0.55
     متعلقه
    -0.53
     bezeichneter
    -0.52
    TintMode
    -0.51
     okaz
    -0.50
    izzera
    -0.50
    aronne
    -0.50
    fontein
    -0.50
    POSITIVE LOGITS
    steuer
    0.55
     inside
    0.52
     treated
    0.50
    Treating
    0.48
     ComVisible
    0.47
    სქოლიო
    0.47
     NavController
    0.45
     Treating
    0.44
    PMailer
    0.44
     menutup
    0.44
    Activations Density 0.027%

    No Known Activations