© 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. 3865
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
    Datuak
    -0.56
     jaune
    -0.54
     correctes
    -0.53
    SizeF
    -0.52
     hansen
    -0.50
     Hymn
    -0.50
    χν
    -0.49
    ALLY
    -0.49
    WindowListener
    -0.49
     cartões
    -0.49
    POSITIVE LOGITS
    stdc
    0.59
    AddTagHelper
    0.54
     GenerationType
    0.51
     ujednoznacz
    0.48
     <=",
    0.47
    Personendaten
    0.47
    WebMethod
    0.46
    ActionCreators
    0.46
    permitAll
    0.46
    IsContent
    0.45
    Activations Density 0.000%

    No Known Activations