© 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. 76349
    Prev
    Next
    INDEX
    Explanations

    small size

    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
    Huge
    -0.87
     Huge
    -0.87
    Massive
    -0.83
     enormes
    -0.81
     Massive
    -0.80
     énorm
    -0.79
     masiva
    -0.78
    Large
    -0.77
     énorme
    -0.77
     Large
    -0.76
    POSITIVE LOGITS
     small
    1.47
     short
    1.38
     brief
    1.31
     minor
    1.31
     mild
    1.23
     modest
    1.21
    small
    1.13
     simple
    1.11
     slight
    1.09
     light
    1.05
    Activations Density 0.000%

    No Known Activations