© 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. 5-CLT-HP
    7. 5135
    Prev
    Next
    INDEX
    Explanations

    food, meals

    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
    takings
    -0.56
    times
    -0.52
    time
    -0.48
    mentable
    -0.46
    chandising
    -0.46
    ään
    -0.45
    halb
    -0.45
    vain
    -0.45
    RoutingModule
    -0.45
     progetti
    -0.44
    POSITIVE LOGITS
    rrggbb
    0.71
     surla
    0.68
     of
    0.66
    ChildScrollView
    0.66
    Rhestr
    0.65
    ContentAsync
    0.64
    CDCl
    0.63
    IVEREF
    0.62
     consisting
    0.60
    parsedMessage
    0.58
    Activations Density 0.001%

    No Known Activations