© 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. 94001
    Prev
    Next
    INDEX
    Explanations

    punctuation and "and"

    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
    ophysical
    -0.56
     WebDriverWait
    -0.50
    houette
    -0.49
    ORPG
    -0.48
    AutoresizingMask
    -0.47
     Grand
    -0.47
    uldron
    -0.46
    NonQuery
    -0.45
    bidities
    -0.45
    ruppen
    -0.45
    POSITIVE LOGITS
    parsedMessage
    0.68
    Demikian
    0.57
    NameInMap
    0.57
     الحره
    0.56
    Recognition
    0.53
     domicili
    0.52
     autorytatywna
    0.52
     iyon
    0.52
     recev
    0.51
     nonUne
    0.51
    Activations Density 0.009%

    No Known Activations