© 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. 106
    Prev
    Next
    INDEX
    Explanations

    adverbs of time/frequency

    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
    is
    -0.37
    po
    -0.35
    ве
    -0.35
    ing
    -0.35
    es
    -0.34
    to
    -0.34
    isse
    -0.33
    性和
    -0.32
    ド
    -0.32
    hi
    -0.30
    POSITIVE LOGITS
     فريبيس
    1.05
     Called
    1.02
    StoryboardSegue
    1.02
     Known
    1.02
    +#+#
    0.98
    tagHelperRunner
    0.96
     مشين
    0.96
     Uploaded
    0.93
    Personensuche
    0.93
     consultato
    0.93
    Activations Density 0.028%

    No Known Activations