© 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. 0-CLT-HP
    7. 43117
    Prev
    Next
    INDEX
    Explanations

    moving

    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
     Atherton
    -0.43
     Shops
    -0.41
     Dooley
    -0.40
     or
    -0.40
     Kích
    -0.40
     Packard
    -0.40
     Improper
    -0.39
     "..\..\
    -0.38
     Orleans
    -0.38
     ग्राहक
    -0.38
    POSITIVE LOGITS
    ContentAsync
    0.92
     كومونز
    0.85
    <bos>
    0.83
    /**
    0.66
     محفوظة
    0.61
    styleType
    0.59
    FunctionFlags
    0.58
     Xuan
    0.55
    ."]
    0.55
    TargetApi
    0.55
    Activations Density 0.281%

    No Known Activations