© 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. 4020
    Prev
    Next
    INDEX
    Explanations

    to or colon

    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
     SqlParameter
    -0.56
     strdup
    -0.53
    RunAsync
    -0.52
    Base
    -0.51
    academia
    -0.50
    <bos>
    -0.50
    ContentAsync
    -0.50
     صوتيه
    -0.50
     للمعارف
    -0.48
     coster
    -0.47
    POSITIVE LOGITS
     that
    0.81
    InputModule
    0.53
     насељу
    0.52
     bahwa
    0.51
    that
    0.50
     THAT
    0.47
     nó
    0.47
    AndEndTag
    0.46
    styleUrls
    0.45
     Kerja
    0.45
    Activations Density 0.001%

    No Known Activations