© 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. 3104
    Prev
    Next
    INDEX
    Explanations

    Abbreviations or codes

    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
    ########.
    -0.62
     mergeFrom
    -0.62
    tagHelperRunner
    -0.60
    chelles
    -0.59
     tartalomajánló
    -0.57
    MessageTagHelper
    -0.56
    Nonnull
    -0.52
     vPvB
    -0.52
    FieldDescriptor
    -0.50
    RUnlock
    -0.50
    POSITIVE LOGITS
    CodeAttribute
    0.66
    centralwidget
    0.54
    hogy
    0.54
    ʋ
    0.54
    soft
    0.50
    StoryboardSegue
    0.49
     NSCoder
    0.48
    gru
    0.48
     Eind
    0.48
    sous
    0.47
    Activations Density 0.001%

    No Known Activations