© 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. 1-CLT-HP
    7. 9582
    Prev
    Next
    INDEX
    Explanations

    osa

    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
    GEBURTSDATUM
    -0.54
    queryInterface
    -0.48
    rem
    -0.44
    wer
    -0.42
    zki
    -0.42
    XtraReports
    -0.40
    associated
    -0.40
    PhysRev
    -0.39
     princí
    -0.39
    طبيق
    -0.38
    POSITIVE LOGITS
    WriteBarrier
    0.72
    ✨:
    0.68
    Geplaatst
    0.64
     Sodom
    0.64
    ljeno
    0.63
     Hache
    0.61
     doInBackground
    0.60
     cartesian
    0.60
     mosques
    0.59
     apostolic
    0.59
    Activations Density 0.073%

    No Known Activations