© 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. 0-CLT-HP
    7. 97342
    Prev
    Next
    INDEX
    Explanations

    past-tense verbs

    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
    .
    -0.56
     חיצוניים
    -0.54
     mesmos
    -0.52
     guerres
    -0.51
     specifiche
    -0.50
    antaranya
    -0.50
     cuales
    -0.49
    ;
    -0.49
     hombro
    -0.48
    u
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.86
     '\\;'
    0.82
     disambiguazione
    0.80
    Personendaten
    0.80
    hyrchwyd
    0.80
    esterday
    0.79
     nakalista
    0.79
     noDo
    0.75
    <bos>
    0.75
    ParallelGroup
    0.74
    Activations Density 0.070%

    No Known Activations