© 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. 2608
    Prev
    Next
    INDEX
    Explanations

    conditions, circumstances

    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
    SourceChecksum
    -0.73
    ValueGeneration
    -0.65
     CreateTagHelper
    -0.63
    хьтан
    -0.61
     المعيارى
    -0.61
    ValueStyle
    -0.59
    appellant
    -0.57
     defaultstate
    -0.57
    TagMode
    -0.57
    sidemargin
    -0.56
    POSITIVE LOGITS
    aneously
    0.49
     termites
    0.46
    __":
    0.44
    プリング
    0.43
     الرياضيه
    0.43
    icie
    0.43
     >=",
    0.42
     mineralization
    0.42
     fullt
    0.42
     your
    0.41
    Activations Density 0.001%

    No Known Activations