© 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. 5-CLT-HP
    7. 92789
    Prev
    Next
    INDEX
    Explanations

    a

    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
    <bos>
    -0.67
     BoxFit
    -0.56
    RectangleBorder
    -0.54
    Pratique
    -0.53
     ✭✭
    -0.50
    تقاوى
    -0.49
    
    -0.48
    Personendaten
    -0.47
     dépos
    -0.47
    ism
    -0.47
    POSITIVE LOGITS
    Jîn
    0.61
    andExpect
    0.54
    цездатний
    0.52
     second
    0.51
     new
    0.50
    MigrationBuilder
    0.49
    AndroidJUnit
    0.49
     referrerpolicy
    0.48
    ngdoc
    0.48
     Numerade
    0.47
    Activations Density 0.008%

    No Known Activations