© 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. 93643
    Prev
    Next
    INDEX
    Explanations

    the

    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
     
    -0.61
     really
    -0.51
    <eos>
    -0.49
     $
    -0.46
     politici
    -0.45
    enumi
    -0.44
     fall
    -0.42
     You
    -0.42
     ladies
    -0.42
     are
    -0.41
    POSITIVE LOGITS
    Geplaatst
    0.82
    webElementXpaths
    0.76
     feroit
    0.74
    rungsseite
    0.73
     مشين
    0.73
     larmes
    0.71
     avoient
    0.71
     stället
    0.71
    帖最后由
    0.71
     enfans
    0.69
    Activations Density 0.214%

    No Known Activations