© 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. 94436
    Prev
    Next
    INDEX
    Explanations

    software, organization

    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
    Ikr
    -0.52
    LookAnd
    -0.51
    disposing
    -0.43
     wavelength
    -0.43
    hamcrest
    -0.42
    तीय
    -0.40
     figure
    -0.40
     themselves
    -0.40
     useSelector
    -0.39
    INCRE
    -0.39
    POSITIVE LOGITS
     nakalista
    0.70
     препратки
    0.65
     wrote
    0.60
     CURIAM
    0.59
    wrote
    0.58
    }],
    0.57
     člá
    0.57
     write
    0.56
    ="<?=$
    0.56
    %)$
    0.54
    Activations Density 0.000%

    No Known Activations