© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15411
    Prev
    Next
    INDEX
    Explanations

    astronomy research

    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
     otomatig
    -0.50
     <=",
    -0.47
    StoryboardSegue
    -0.47
     poitrine
    -0.47
     chaleur
    -0.46
    ByExample
    -0.45
    ,
    -0.44
     goutte
    -0.43
     jspb
    -0.43
    󠁢
    -0.43
    POSITIVE LOGITS
    --){
    0.67
     Pamp
    0.65
    '][$
    0.65
    ]<<"
    0.63
     consultato
    0.62
    WindowConstants
    0.61
    "]();
    0.60
    ]}>
    0.57
    NUMX
    0.57
     asunder
    0.57
    Activations Density 0.020%

    No Known Activations