© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12000
    Prev
    Next
    INDEX
    Explanations

    definition

    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
     definition
    -0.82
    Definition
    -0.74
     Definition
    -0.70
    DEFINITION
    -0.69
     definitions
    -0.66
    definition
    -0.65
     defin
    -0.61
     Defin
    -0.58
     Def
    -0.56
     define
    -0.56
    POSITIVE LOGITS
    Gruss
    0.55
     ویکی‌پدی
    0.54
    setString
    0.53
     DONE
    0.51
     infos
    0.51
     חיצוניים
    0.50
     Warlock
    0.50
     PMID
    0.50
    MessageState
    0.50
     files
    0.50
    Activations Density 0.086%

    No Known Activations