© 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. 46
    Prev
    Next
    INDEX
    Explanations

    from

    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
    Predecesor
    -0.51
    期刊论文
    -0.47
    ̓
    -0.46
    AsUp
    -0.45
     akum
    -0.45
    Děkuji
    -0.44
    اون
    -0.44
     puissiez
    -0.43
    äjä
    -0.43
     susah
    -0.43
    POSITIVE LOGITS
     Figure
    0.59
     figure
    0.59
     насељу
    0.57
    PREDICT
    0.56
    /**
    0.55
     nahilalakip
    0.55
     eksemp
    0.53
    #
    0.53
    migrationBuilder
    0.53
    RTGC
    0.53
    Activations Density 0.003%

    No Known Activations