© 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. 4-CLT-HP
    7. 1022
    Prev
    Next
    INDEX
    Explanations

    numbers and specifications

    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
     Efq
    -0.96
     itſelf
    -0.81
     CreateTagHelper
    -0.80
     pinulongan
    -0.80
     snippetHide
    -0.73
     myſelf
    -0.73
     ſever
    -0.73
    CppMethod
    -0.71
     uLocal
    -0.71
    -------
    -0.69
    POSITIVE LOGITS
    0
    0.94
    7
    0.77
    5
    0.77
    4
    0.75
    6
    0.73
    8
    0.73
    3
    0.73
    2
    0.71
    9
    0.62
    1
    0.59
    Activations Density 0.001%

    No Known Activations