© 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. 73054
    Prev
    Next
    INDEX
    Explanations

    mattresses and beds

    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
    Personensuche
    -0.93
    RTSC
    -0.71
    rungsseite
    -0.70
    InstanceState
    -0.66
    ChildScrollView
    -0.65
     mxArray
    -0.63
    binant
    -0.62
    ganu
    -0.59
     surla
    -0.58
     onData
    -0.58
    POSITIVE LOGITS
     head
    0.75
     memory
    0.72
     springs
    0.61
     Temp
    0.60
     Memory
    0.59
     Head
    0.58
    head
    0.57
    memory
    0.57
     MEMORY
    0.56
    Memory
    0.56
    Activations Density 0.003%

    No Known Activations