© 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. 1-CLT-HP
    7. 14071
    Prev
    Next
    INDEX
    Explanations

    Xbox or Playstation

    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
     Hệ
    -0.56
    uminense
    -0.54
     hochzeit
    -0.52
     Roskov
    -0.52
    eavor
    -0.52
    BufferException
    -0.51
    AutoScaleMode
    -0.50
    ummy
    -0.50
     voks
    -0.49
    ThroughAttribute
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    0.57
    ting
    0.51
    ResumeLayout
    0.49
    urlpatterns
    0.48
    servable
    0.47
    RunWith
    0.47
    tung
    0.46
    PRWEB
    0.46
     ngang
    0.45
    لاق
    0.45
    Activations Density 0.028%

    No Known Activations