© 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. 14759
    Prev
    Next
    INDEX
    Explanations

    lattices and seating

    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
     seated
    -1.48
    seated
    -1.10
     seeded
    -0.67
    umumkan
    -0.58
     Waray
    -0.56
    ynb
    -0.56
     Autorizaciones
    -0.52
     gesetzt
    -0.51
    jsii
    -0.50
    contentLoaded
    -0.49
    POSITIVE LOGITS
    WebElementEntity
    0.68
    DockStyle
    0.63
    ing
    0.60
    انيف
    0.60
     CURLOPT
    0.60
    IBOutlet
    0.59
    instruction
    0.52
    jspb
    0.52
    (@"%@",
    0.52
    HasMaxLength
    0.51
    Activations Density 0.241%

    No Known Activations