© 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. 0-CLT-HP
    4. 41704
    Prev
    Next
    INDEX
    Explanations

    tracking and reporting

    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
     Efq
    -0.72
    `,
    
    -0.70
    ✨:
    -0.69
     myſelf
    -0.69
     reaſon
    -0.67
     RouterModule
    -0.66
    ]")]
    -0.66
    ]),
    
    -0.66
     photolibrary
    -0.65
    ]){
    
    -0.65
    POSITIVE LOGITS
     for
    0.56
    .
    0.51
    ,
    0.51
    WithIOException
    0.49
    Trama
    0.48
    Viungo
    0.47
     to
    0.46
    (
    0.46
     and
    0.45
     (
    0.44
    Activations Density 0.054%

    No Known Activations