© 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. 5-CLT-HP
    7. 4465
    Prev
    Next
    INDEX
    Explanations

    son

    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
    Cyfeiriadau
    -0.50
    sbury
    -0.48
    ikou
    -0.44
    Autoritní
    -0.44
    xhttp
    -0.43
    IEV
    -0.43
    wart
    -0.43
    unid
    -0.43
    ("")]
    -0.43
     he
    -0.43
    POSITIVE LOGITS
     of
    0.88
    utilisons
    0.68
    #+#
    0.61
    WriteTagHelper
    0.60
    pulumi
    0.57
    AddHtmlAttribute
    0.57
    rungsseite
    0.56
     propOrder
    0.54
    SequentialGroup
    0.54
    มาะ
    0.54
    Activations Density 0.001%

    No Known Activations