© 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. 1-CLT-HP
    7. 14567
    Prev
    Next
    INDEX
    Explanations

    massless

    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
    ]){
    -0.65
     '\\;'
    -0.62
    StreetMap
    -0.60
    WindowConstants
    -0.60
    ")]
    -0.59
     estekak
    -0.59
    ]),
    -0.59
    ibm
    -0.59
    TagMode
    -0.58
    uxxxx
    -0.58
    POSITIVE LOGITS
    interopRequire
    0.45
    ọn
    0.44
     Soyez
    0.44
     برانيه
    0.43
    пти
    0.42
     noqa
    0.42
     Plaster
    0.42
    send
    0.41
    pat
    0.41
     master
    0.41
    Activations Density 0.024%

    No Known Activations