© 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. 4-CLT-HP
    7. 1122
    Prev
    Next
    INDEX
    Explanations

    Something collapsing or declining

    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
    GEBURTSDATUM
    -0.52
     defStyleAttr
    -0.48
     AttributeSet
    -0.48
    multer
    -0.47
    ########.
    -0.46
    SharedDtor
    -0.42
    QName
    -0.42
     createState
    -0.42
     دیکھیے
    -0.42
    Cyfeiriadau
    -0.41
    POSITIVE LOGITS
     Communications
    0.61
     prey
    0.60
    "](
    0.57
    queryInterface
    0.57
    __*/
    0.57
    Communications
    0.57
     विश्वसनीयता
    0.56
     silent
    0.55
     Girls
    0.54
    "}"
    0.54
    Activations Density 0.004%

    No Known Activations