© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10704
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    󠁿
    -0.62
     gynnwys
    -0.57
     Era
    -0.57
    ípios
    -0.57
    TabPage
    -0.55
    ésia
    -0.54
    Personensuche
    -0.53
    asgi
    -0.53
    antaine
    -0.52
     era
    -0.51
    POSITIVE LOGITS
    1
    0.61
    0
    0.59
    7
    0.52
    3
    0.51
    4
    0.50
    2
    0.49
    6
    0.48
    RunWith
    0.48
    9
    0.46
    <bos>
    0.45
    Activations Density 0.027%

    No Known Activations