© 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. 96396
    Prev
    Next
    INDEX
    Explanations

    finding the best way

    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
     Biôgrafia
    -0.67
     bäst
    -0.66
     ExecuteAsync
    -0.64
    SourceChecksum
    -0.64
    IndentedString
    -0.64
     humaines
    -0.61
     najlepiej
    -0.60
     réforme
    -0.59
    })`
    -0.59
     ISNI
    -0.58
    POSITIVE LOGITS
    клопе
    0.51
     close
    0.49
     to
    0.48
    kter
    0.45
    berra
    0.45
     not
    0.45
    AddColumn
    0.45
    phosa
    0.42
     who
    0.42
     Who
    0.41
    Activations Density 0.006%

    No Known Activations