© 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. 0-CLT-HP
    7. 95389
    Prev
    Next
    INDEX
    Explanations

    Johnston

    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
     pinulongan
    -0.83
    Tikang
    -0.69
    SizeF
    -0.67
     متعلقه
    -0.65
    phalt
    -0.63
    fully
    -0.62
    ngdoc
    -0.61
    DebuggerNonUser
    -0.59
    存于互联网档案馆
    -0.57
     correctes
    -0.57
    POSITIVE LOGITS
     Sofía
    0.54
     scania
    0.53
    y
    0.52
     Darío
    0.50
     Universitario
    0.50
     Colonia
    0.49
     Baltic
    0.47
     Cæsar
    0.47
     shipwreck
    0.47
    PreferredItem
    0.47
    Activations Density 0.073%

    No Known Activations