© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2470
    Prev
    Next
    INDEX
    Explanations

    technical writing/data

    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
    ])){
    -0.60
     disparu
    -0.59
    ])))
    -0.59
     fumée
    -0.57
     démarrer
    -0.56
     hâte
    -0.54
    toHaveBeenCalled
    -0.54
    ArgsConstructor
    -0.54
    )];
    -0.52
    garek
    -0.52
    POSITIVE LOGITS
    databind
    0.55
    migrationBuilder
    0.54
     wretch
    0.53
     electronics
    0.50
     electr
    0.48
    gdx
    0.47
     INSTITUTE
    0.47
    дента
    0.47
     neutrons
    0.47
     macrop
    0.46
    Activations Density 0.007%

    No Known Activations