© 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. 0-CLT-HP
    7. 93362
    Prev
    Next
    INDEX
    Explanations

    Health and Living Conditions

    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
     tank
    -1.18
     صوتيه
    -1.14
     виправивши
    -1.13
     tanks
    -1.12
    tank
    -1.07
    MigrationBuilder
    -1.06
    DockStyle
    -1.04
     <=",
    -1.04
     Tank
    -1.03
    Tank
    -1.03
    POSITIVE LOGITS
     small
    0.42
     
    0.41
    3
    0.41
     non
    0.39
    2
    0.38
     Jogo
    0.35
    ↵↵
    0.35
    est
    0.35
    istar
    0.34
    -
    0.34
    Activations Density 0.256%

    No Known Activations