© 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. 5-CLT-HP
    7. 93859
    Prev
    Next
    INDEX
    Explanations

    conversational text

    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
     TestBed
    -0.71
     protoimpl
    -0.66
    afficheront
    -0.64
    DOCTYPE
    -0.63
    Tikang
    -0.59
     Мексичка
    -0.59
    ंदीखरीदारी
    -0.58
     ModelExpression
    -0.57
    thâu
    -0.57
    SpringBootTest
    -0.55
    POSITIVE LOGITS
     piuttosto
    0.66
     rather
    0.63
    oterapia
    0.61
     Rather
    0.60
     quelques
    0.60
     occasional
    0.59
     some
    0.58
     chinoise
    0.58
     something
    0.57
    DispatchToProps
    0.54
    Activations Density 0.003%

    No Known Activations