© 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. 0-CLT-HP
    7. 1764
    Prev
    Next
    INDEX
    Explanations

    Gro

    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
    +#+#
    -0.93
     newBuilder
    -0.81
    riwal
    -0.81
    rungsseite
    -0.79
    TagMode
    -0.78
    VersionUID
    -0.77
    MigrationBuilder
    -0.75
    IntoConstraints
    -0.73
    XmlAccessType
    -0.71
    stairs
    -0.66
    POSITIVE LOGITS
     Pristupljeno
    0.42
    </blockquote>
    0.40
     Atmospheric
    0.39
     let
    0.38
     Express
    0.38
    uffer
    0.38
     atmospheric
    0.37
    宣
    0.37
    jstor
    0.36
    ................
    0.36
    Activations Density 0.117%

    No Known Activations