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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93265
    Prev
    Next
    INDEX
    Explanations

    code and errors

    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
     wireType
    -0.85
     ExecuteAsync
    -0.72
     initComponents
    -0.71
    styleType
    -0.65
     AttributeSet
    -0.60
    atype
    -0.58
     ligiloj
    -0.57
    >",
    -0.56
    WriteTagHelper
    -0.56
     AllMovie
    -0.55
    POSITIVE LOGITS
    2
    0.83
    0
    0.61
    FE
    0.52
     Picchu
    0.45
    Xk
    0.43
    𝐗
    0.42
    icol
    0.42
    FF
    0.42
     mk
    0.41
    snow
    0.41
    Activations Density 0.003%

    No Known Activations