© 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. 13774
    Prev
    Next
    INDEX
    Explanations

    quantity

    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
     ProtoMessage
    -0.64
    ngdoc
    -0.62
     INTERESAR
    -0.60
    <%@
    -0.60
     vPvB
    -0.59
    riwal
    -0.59
    canestro
    -0.59
    anyahu
    -0.59
     شهرد
    -0.58
    yntaxException
    -0.57
    POSITIVE LOGITS
    makeConstraints
    0.51
    ].)
    0.43
    ishy
    0.41
    здание
    0.40
    cipation
    0.40
     child
    0.40
    :✨
    0.40
    ört
    0.40
    BrowserModule
    0.40
    extAlignment
    0.39
    Activations Density 0.009%

    No Known Activations