© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93141
    Prev
    Next
    INDEX
    Explanations

    physical appearance

    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
     kasarigan
    -0.57
    routeProvider
    -0.53
    TabIndex
    -0.52
    stateProvider
    -0.48
    ########.
    -0.48
     transférez
    -0.48
    RenderAtEndOf
    -0.47
     pinulongan
    -0.47
     Disclosure
    -0.47
    cadeira
    -0.46
    POSITIVE LOGITS
    ScopeManager
    0.66
    sphin
    0.59
    rrggbb
    0.57
    shadowRadius
    0.57
    sidemargin
    0.51
    processable
    0.50
    tasche
    0.49
    Aktualisiert
    0.49
    Références
    0.48
    Kanpo
    0.48
    Activations Density 0.006%

    No Known Activations