© 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. 9006
    Prev
    Next
    INDEX
    Explanations

    probe/Hub

    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
     Hub
    -1.32
    Hub
    -1.24
     hub
    -1.20
     Hubbard
    -1.13
     HUB
    -1.10
     hubs
    -0.99
    hub
    -0.92
    HUB
    -0.91
     probe
    -0.78
     Hubert
    -0.73
    POSITIVE LOGITS
    baran
    0.52
    bar
    0.50
    s
    0.49
    bars
    0.47
    word
    0.46
    addLast
    0.46
    member
    0.45
    line
    0.45
     ProtoMessage
    0.45
    moid
    0.44
    Activations Density 0.016%

    No Known Activations