© 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. 92958
    Prev
    Next
    INDEX
    Explanations

    vascular

    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
    ритори
    -0.65
    <eos>
    -0.63
    (!__
    -0.55
    IUrlHelper
    -0.54
    ,”
    -0.54
    SourceChecksum
    -0.54
    ,"%
    -0.51
    ."],
    -0.49
     (…)
    -0.48
     himo
    -0.47
    POSITIVE LOGITS
    Enllaces
    0.59
    Vidite
    0.57
    Παραπομπές
    0.56
     Efq
    0.56
    scalatest
    0.54
    abstractmethod
    0.53
    Hentet
    0.53
     שוליים
    0.52
    Referências
    0.51
    Referències
    0.51
    Activations Density 0.001%

    No Known Activations