© 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. 0-CLT-HP
    7. 94706
    Prev
    Next
    INDEX
    Explanations

    legal/safety related notices

    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
     wrong
    -0.97
     Wrong
    -0.93
     WRONG
    -0.93
     AssemblyVersion
    -0.91
    wrong
    -0.91
     Audiodateien
    -0.90
    Vidite
    -0.89
     mystery
    -0.88
    Хьажоргаш
    -0.88
     snippetHide
    -0.87
    POSITIVE LOGITS
    i
    0.57
    e
    0.55
     the
    0.49
     
    0.49
    hand
    0.49
     Coll
    0.48
    coll
    0.48
     or
    0.47
     is
    0.46
    Coll
    0.46
    Activations Density 1.490%

    No Known Activations