© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3997
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    OGND
    -0.63
     '{@
    -0.59
    prepareStatement
    -0.58
    makeConstraints
    -0.57
    [++
    -0.57
    setVerticalGroup
    -0.55
    onAttach
    -0.55
    migrationBuilder
    -0.54
     yow
    -0.53
    
    -0.51
    POSITIVE LOGITS
    rrggbb
    0.62
     eagles
    0.60
     innehå
    0.55
     rischi
    0.54
     Infórmanos
    0.54
    ⓧ
    0.54
     Eagles
    0.54
    Personendaten
    0.53
    eagle
    0.53
    veien
    0.52
    Activations Density 0.006%

    No Known Activations