© 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. 43886
    Prev
    Next
    INDEX
    Explanations

    posted

    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
     postings
    -1.23
     posted
    -1.02
    Posted
    -1.02
     posting
    -0.96
     ―――――
    -0.96
     Posting
    -0.95
     ་་
    -0.94
     ſind
    -0.91
     posts
    -0.89
    CppMethod
    -0.89
    POSITIVE LOGITS
     
    0.77
    .
    0.72
     on
    0.68
    ,
    0.68
     of
    0.68
     for
    0.68
     and
    0.65
     (
    0.65
     at
    0.64
     The
    0.63
    Activations Density 0.122%

    No Known Activations