© 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. 5-CLT-HP
    7. 2860
    Prev
    Next
    INDEX
    Explanations

    take

    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
     незавершена
    -1.03
    SourceChecksum
    -0.99
    Enllaces
    -0.86
    ########.
    -0.84
    +#+#
    -0.80
     صوتيه
    -0.77
     autorytatywna
    -0.75
     يتيمه
    -0.74
    transQ
    -0.74
     وتسجيلات
    -0.73
    POSITIVE LOGITS
     special
    0.81
     great
    0.74
     note
    0.69
     time
    0.68
     into
    0.66
     extra
    0.61
     especial
    0.58
     care
    0.58
     plenty
    0.56
     particular
    0.55
    Activations Density 0.001%

    No Known Activations