© 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. 5-CLT-HP
    4. 94332
    Prev
    Next
    INDEX
    Explanations

    corn

    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
     nonatomic
    -0.58
     Paths
    -0.54
     useAuth
    -0.53
     Handles
    -0.51
    ISupport
    -0.51
    alanta
    -0.50
    "]').
    -0.50
    fjspx
    -0.50
     Letters
    -0.49
    Rena
    -0.48
    POSITIVE LOGITS
    addCriterion
    0.63
    MessageTagHelper
    0.56
     disambiguazione
    0.55
    cob
    0.53
    oredCriteria
    0.49
    ices
    0.49
    Hentet
    0.48
    MLLoader
    0.48
     referenties
    0.47
    Aholisi
    0.47
    Activations Density 0.003%

    No Known Activations