© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2245
    Prev
    Next
    INDEX
    Explanations

    valves

    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
     size
    -1.17
     SIZE
    -0.94
     sized
    -0.94
    size
    -0.91
     tamaño
    -0.91
     sizes
    -0.90
     taille
    -0.89
    ConstraintMaker
    -0.89
    sized
    -0.89
     Size
    -0.88
    POSITIVE LOGITS
    tonsoft
    0.58
     Ends
    0.48
    bosis
    0.48
     {?>
    0.47
    nocache
    0.47
     bParam
    0.46
    Tome
    0.45
    yuki
    0.44
    tır
    0.44
    groupBox
    0.44
    Activations Density 0.015%

    No Known Activations