© 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. 4-CLT-HP
    7. 609
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ArgsConstructor
    -0.59
     noqa
    -0.49
    ||}
    -0.49
    HasBeenSet
    -0.49
     pono
    -0.48
    FieldBuilder
    -0.44
    Karakteristik
    -0.42
     Namens
    -0.42
    HasForeignKey
    -0.42
    PasswordEncoder
    -0.42
    POSITIVE LOGITS
    InputTagHelper
    0.79
    verwijspagina
    0.64
     disambiguazione
    0.60
     ProductService
    0.60
    出版年
    0.59
     ligiloj
    0.59
     work
    0.59
    arriver
    0.58
     ORGANISM
    0.57
     hObject
    0.57
    Activations Density 0.005%

    No Known Activations