© 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. 301
    Prev
    Next
    INDEX
    Explanations

    sad

    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
     Audiodateien
    -0.84
     الحره
    -0.70
    grimas
    -0.60
     surla
    -0.57
    bbene
    -0.57
    المناصب
    -0.56
     uſed
    -0.56
     xdrive
    -0.56
     }}$}
    -0.56
    IntoConstraints
    -0.55
    POSITIVE LOGITS
    MessageTagHelper
    0.59
     mes
    0.51
    belie
    0.44
     dress
    0.44
     BorderRadius
    0.44
    textTheme
    0.44
     CWE
    0.43
     dem
    0.42
    Geplaatst
    0.42
    createCanvas
    0.41
    Activations Density 0.000%

    No Known Activations