© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1445
    Prev
    Next
    INDEX
    Explanations

    |

    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
     |
    -1.92
    ｜
    -1.06
     |
    -0.97
     │
    -0.92
     $|
    -0.91
     |\
    -0.85
     ||
    -0.85
    │
    -0.85
    |"
    -0.82
    Personensuche
    -0.82
    POSITIVE LOGITS
    (
    0.71
    .
    0.66
    "
    0.62
    )";
    0.61
    ')))
    0.60
     Greater
    0.59
     The
    0.58
     
    0.57
     a
    0.56
    $
    0.56
    Activations Density 0.357%

    No Known Activations