© 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. 72345
    Prev
    Next
    INDEX
    Explanations

    :

    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
    RLock
    -0.41
    GroupLayout
    -0.40
    @@
    -0.40
    merie
    -0.39
    Hey
    -0.37
    mler
    -0.36
     pháp
    -0.36
    kap
    -0.36
     kad
    -0.35
     Burg
    -0.35
    POSITIVE LOGITS
    CodedInputStream
    0.84
    LookAnd
    0.81
    principalColumn
    0.80
    UnusedPrivate
    0.79
     GenerationType
    0.79
     ProtoMessage
    0.79
    UseVisualStyle
    0.77
    endphp
    0.76
     CreateTagHelper
    0.75
    出版年
    0.74
    Activations Density 0.000%

    No Known Activations