© 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. 0-CLT-HP
    7. 93572
    Prev
    Next
    INDEX
    Explanations

    importance

    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
     determining
    -1.28
     determine
    -1.13
     determines
    -1.05
     defining
    -1.05
     Determining
    -1.04
     menentukan
    -0.98
    determine
    -0.98
     decisive
    -0.97
    Determining
    -0.97
    determin
    -0.93
    POSITIVE LOGITS
    ist
    0.56
     coach
    0.48
    i
    0.46
    ists
    0.45
    ództ
    0.44
    法的
    0.43
     Mathem
    0.43
    Raw
    0.43
    Rujukan
    0.43
    __()
    0.42
    Activations Density 1.303%

    No Known Activations