© 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. 20-CLT-HP
    7. 72599
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · 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
     McCarty
    -0.48
    FTFY
    -0.47
    Clo
    -0.44
    JKLM
    -0.43
    setopt
    -0.43
     lau
    -0.43
    gep
    -0.42
     writable
    -0.42
     Larkin
    -0.42
    ်း
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.81
    interopRequire
    0.79
     GenerationType
    0.79
    fromnode
    0.68
    NameInMap
    0.65
    WriteLiteral
    0.65
    awtextra
    0.65
    PostConstruct
    0.64
    styleType
    0.63
    TagMode
    0.63
    Activations Density 0.002%

    No Known Activations