© 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. 5-CLT-HP
    7. 487
    Prev
    Next
    INDEX
    Explanations

    to

    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
     realizing
    -0.60
     daß
    -0.54
     believing
    -0.54
     realizes
    -0.53
     accomplishment
    -0.52
     saying
    -0.51
    saying
    -0.50
     Planeta
    -0.49
     committing
    -0.49
    andaag
    -0.49
    POSITIVE LOGITS
     resourceCulture
    0.70
    SourceChecksum
    0.65
    CppMethod
    0.62
    tagHelperRunner
    0.60
    NameInMap
    0.59
    GEBURTSDATUM
    0.59
    ValueStyle
    0.58
    MLLoader
    0.56
     Aid
    0.56
     Track
    0.56
    Activations Density 0.000%

    No Known Activations