© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 93702
    Prev
    Next
    INDEX
    Explanations

    images

    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
     pinulongan
    -0.76
    цездатний
    -0.75
    }))
    
    -0.72
    }));
    
    -0.69
     resourceCulture
    -0.68
    IntoConstraints
    -0.67
    XmlAccessType
    -0.65
     autorytatywna
    -0.64
    ]--;
    -0.63
    ]};
    -0.63
    POSITIVE LOGITS
     shows
    0.61
     illustrates
    0.49
     on
    0.49
     reveals
    0.47
     mentions
    0.47
     plumas
    0.46
     combines
    0.46
     deals
    0.46
     portrays
    0.45
     suggests
    0.45
    Activations Density 0.004%

    No Known Activations