© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5568
    Prev
    Next
    INDEX
    Explanations

    after

    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
     Paglinawan
    -0.67
    unistd
    -0.60
     RouterModule
    -0.59
     rhestr
    -0.59
    ptonshire
    -0.59
    endpush
    -0.58
     <<<<<<<<<<<<<<
    -0.58
    scrapy
    -0.57
    ]")]
    -0.56
    //
    -0.56
    POSITIVE LOGITS
    StructEnd
    0.57
     beyond
    0.48
    Kjelder
    0.47
     sufficiently
    0.45
     poffe
    0.44
    estroyer
    0.44
     oficialmente
    0.44
     Normdatei
    0.42
     torn
    0.42
     awakened
    0.42
    Activations Density 0.027%

    No Known Activations