© 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. 77295
    Prev
    Next
    INDEX
    Explanations

    Text fragments

    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
    tagHelperRunner
    -0.55
    +:+
    -0.51
    BagConstraints
    -0.49
    audiovisuel
    -0.49
    ysacchar
    -0.48
     jScrollPane
    -0.48
     propOrder
    -0.46
    ات
    -0.46
    anele
    -0.45
    rometry
    -0.45
    POSITIVE LOGITS
    hook
    0.48
    spin
    0.47
    rad
    0.45
    w
    0.44
    spring
    0.43
    br
    0.43
    kind
    0.43
    j
    0.43
    spine
    0.43
    kir
    0.43
    Activations Density 0.000%

    No Known Activations