© 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. 20-CLT-HP
    7. 71744
    Prev
    Next
    INDEX
    Explanations

    greatly

    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
    dafx
    -0.84
     invokingState
    -0.84
     autorytatywna
    -0.82
     Wiktionnaire
    -0.80
     تضيفلها
    -0.80
    SequentialGroup
    -0.79
    rawDesc
    -0.78
    曖昧さ回避
    -0.77
    KEYCODE
    -0.77
     OnTriggerEnter
    -0.77
    POSITIVE LOGITS
     ap
    0.37
     AP
    0.32
    ás
    0.31
     aqu
    0.31
     kap
    0.31
     thankfully
    0.31
     TextAppearance
    0.31
    ә
    0.31
    ather
    0.30
    ly
    0.30
    Activations Density 0.003%

    No Known Activations