© 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. 15070
    Prev
    Next
    INDEX
    Explanations

    network nodes and sockets

    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
    socket
    -0.89
     socket
    -0.81
     Socket
    -0.69
    Rüyada
    -0.63
    Socket
    -0.60
    node
    -0.59
     node
    -0.58
     ddelweddau
    -0.53
     nodes
    -0.51
    NODE
    -0.51
    POSITIVE LOGITS
    ContentAsync
    0.67
    <bos>
    0.54
    Distribuzione
    0.51
    SharedDtor
    0.50
    Bibliografie
    0.50
     ujednoznacz
    0.50
     turísticos
    0.48
    CodedInputStream
    0.48
     indisponible
    0.48
     uVar
    0.47
    Activations Density 0.025%

    No Known Activations