© 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. 4895
    Prev
    Next
    INDEX
    Explanations

    audio files

    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
     propOrder
    -0.67
    fjspx
    -0.66
    ArgsConstructor
    -0.65
    iprot
    -0.65
    AndEndTag
    -0.64
     jScrollPane
    -0.61
     AssemblyCulture
    -0.61
    RunWith
    -0.60
     betweenstory
    -0.59
    ScopeManager
    -0.57
    POSITIVE LOGITS
     oprot
    0.61
     tjän
    0.56
    ัด
    0.54
    christian
    0.50
    nytt
    0.50
    ecuzione
    0.49
     indietro
    0.48
    aries
    0.48
     risol
    0.48
     gratuits
    0.48
    Activations Density 0.001%

    No Known Activations