© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8860
    Prev
    Next
    INDEX
    Explanations

    hosa

    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
    Negative Logits
    AttributedString
    -0.53
    babe
    -0.52
    StoryboardSegue
    -0.50
    jaguar
    -0.47
    reason
    -0.47
     Babe
    -0.47
    ŚCI
    -0.46
    -------
    -0.46
    AnchorTagHelper
    -0.46
    stunde
    -0.46
    POSITIVE LOGITS
     الرياضيه
    0.59
    AddTagHelper
    0.58
     Mika
    0.56
    fjspx
    0.55
    makeText
    0.54
    ,:]
    0.52
    сылкі
    0.51
     Miko
    0.51
    randomUUID
    0.50
     duke
    0.49
    Activations Density 0.027%

    No Known Activations