© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72230
    Prev
    Next
    INDEX
    Explanations

    "k"

    np_max-act-logits · 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
    mybatisplus
    -0.52
    ApiProperty
    -0.49
     BorderSide
    -0.42
     EDP
    -0.42
     DPD
    -0.41
    APB
    -0.41
    BETH
    -0.40
     Bip
    -0.40
     Buffett
    -0.39
     EDT
    -0.39
    POSITIVE LOGITS
     k
    0.83
     kc
    0.81
     K
    0.71
    kc
    0.69
     kac
    0.68
     κ
    0.68
     ky
    0.65
     kic
    0.64
     KC
    0.64
     ker
    0.64
    Activations Density 0.000%

    No Known Activations