© 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. 20-CLT-HP
    4. 72899
    Prev
    Next
    INDEX
    Explanations

    technical content

    np_max-act-logits · 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
    ,
    -0.53
    väg
    -0.51
    F
    -0.41
    L
    -0.37
     الم
    -0.36
     (
    -0.35
    P
    -0.35
    B
    -0.35
    V
    -0.34
     compresión
    -0.34
    POSITIVE LOGITS
    !")
    
    1.35
     myſelf
    1.34
    .")
    
    1.31
    ."));
    1.28
     itſelf
    1.24
    )");
    
    1.23
    ſelves
    1.23
    .",
    
    1.22
    '},
    
    1.20
    .");
    
    1.19
    Activations Density 0.004%

    No Known Activations