© 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. 4-CLT-HP
    7. 262
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     «
    -0.40
     Jurí
    -0.38
     ū
    -0.37
    "
    -0.36
    «
    -0.35
    
    -0.35
    ,"
    -0.35
     Offisielt
    -0.34
     Blockly
    -0.34
     "
    -0.33
    POSITIVE LOGITS
     Real
    0.79
     Baby
    0.71
    ?
    0.71
     Wikimedijinoj
    0.71
    TheReal
    0.70
    Real
    0.70
     Web
    0.68
     Brings
    0.68
     Popular
    0.66
     ]
    0.65
    Activations Density 0.089%

    No Known Activations