© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 42784
    Prev
    Next
    INDEX
    Explanations

    but

    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
     But
    -1.44
    But
    -1.10
     Nhưng
    -0.79
    Tetapi
    -0.79
    "}")
    -0.75
     Pero
    -0.74
    ]--;
    -0.72
    ")));
    
    -0.71
     eenige
    -0.68
    RectangleBorder
    -0.68
    POSITIVE LOGITS
     if
    1.07
    ,
    0.93
     while
    0.85
     it
    0.84
     there
    0.82
     when
    0.81
     since
    0.80
     as
    0.78
     after
    0.76
     for
    0.74
    Activations Density 1.187%

    No Known Activations