© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94073
    Prev
    Next
    INDEX
    Explanations

    when

    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
    FileInput
    -0.49
    findpost
    -0.49
    }],
    -0.48
     samfun
    -0.47
     meeste
    -0.47
     mäng
    -0.46
    erebbe
    -0.46
     and
    -0.45
    Entering
    -0.45
     debout
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.79
     myſelf
    0.69
    DataAnnotations
    0.66
    fjspx
    0.66
     myself
    0.65
     समीक्षाओं
    0.64
    DebuggerNonUser
    0.63
    UnusedPrivate
    0.62
     itſelf
    0.62
    AddTagHelper
    0.61
    Activations Density 0.003%

    No Known Activations