© 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. 0-CLT-HP
    4. 38676
    Prev
    Next
    INDEX
    Explanations

    tasty

    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
     Theſe
    -0.90
     Anſ
    -0.89
    enderror
    -0.87
     Beſ
    -0.82
     ſever
    -0.82
    enya
    -0.81
    seamnă
    -0.79
    VIRONMENT
    -0.78
    AddTagHelper
    -0.78
     myſelf
    -0.77
    POSITIVE LOGITS
    tor
    0.47
    d
    0.46
    IndentedString
    0.46
     as
    0.45
     we
    0.44
     ti
    0.44
    men
    0.43
     to
    0.42
    rinfo
    0.42
    ',
    0.41
    Activations Density 0.169%

    No Known Activations