© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12201
    Prev
    Next
    INDEX
    Explanations

    Old technology

    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
     Pickett
    -0.73
    ärzt
    -0.51
    RIF
    -0.51
     AssemblyProduct
    -0.50
    shadowRadius
    -0.50
    ########.
    -0.49
    yntaxException
    -0.49
    zések
    -0.48
     esportivo
    -0.47
    venser
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.81
     esternos
    0.61
     pinulongan
    0.59
    kloped
    0.58
    GroupLayout
    0.57
    HtmlAttribute
    0.57
    ingly
    0.56
    WebControls
    0.55
    TypedDataSet
    0.54
    TagHelpers
    0.53
    Activations Density 0.158%

    No Known Activations