© 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. 1381
    Prev
    Next
    INDEX
    Explanations

    Numbers or amounts

    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
     cup
    -1.48
     cups
    -1.47
     Cups
    -1.41
     Cup
    -1.23
    cup
    -1.12
    Cup
    -1.11
    cups
    -1.07
     CUP
    -0.97
    CUP
    -0.88
    tagHelperRunner
    -0.87
    POSITIVE LOGITS
     of
    0.60
    ↵↵
    0.53
    en
    0.51
    If
    0.47
     If
    0.44
    Join
    0.43
    I
    0.43
    er
    0.43
     hoàn
    0.42
    ,
    0.42
    Activations Density 0.205%

    No Known Activations