© 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. 5-CLT-HP
    7. 5877
    Prev
    Next
    INDEX
    Explanations

    domains and code descriptions

    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
     pageContext
    -0.61
    STT
    -0.56
    DebuggerNonUser
    -0.56
    IUrlHelper
    -0.56
    setVerticalGroup
    -0.54
    itename
    -0.54
    lotl
    -0.53
     initComponents
    -0.52
    lifts
    -0.52
     CreateTagHelper
    -0.52
    POSITIVE LOGITS
    bra
    0.76
    BRA
    0.63
    ebra
    0.62
    brom
    0.61
    bral
    0.60
    bras
    0.58
    brar
    0.57
    br
    0.56
    bró
    0.52
    Bra
    0.50
    Activations Density 0.001%

    No Known Activations