© 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. 98237
    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
    rrggbb
    -0.60
    PutMapping
    -0.60
    extAlignment
    -0.56
    ///</
    -0.54
    Cyfeiriadau
    -0.53
    Aiheesta
    -0.53
    MockBean
    -0.53
    andExpect
    -0.51
     Kaly
    -0.49
    dafx
    -0.49
    POSITIVE LOGITS
    comune
    0.59
    embatan
    0.54
    ParallelGroup
    0.54
     Commencez
    0.54
    ();)
    0.53
    ροφο
    0.51
    addContainerGap
    0.50
    ดด
    0.48
     ""))
    0.48
     Paglinawan
    0.48
    Activations Density 0.000%

    No Known Activations