© 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. 0-CLT-HP
    7. 94844
    Prev
    Next
    INDEX
    Explanations

    code/web applications

    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
     lon
    -0.98
    ialis
    -0.77
    ngOnInit
    -0.67
     kaarangay
    -0.66
    evos
    -0.64
    WithIOException
    -0.63
    TemporalType
    -0.62
    stateProvider
    -0.60
    AnchorStyles
    -0.59
    Portail
    -0.57
    POSITIVE LOGITS
    nė
    0.54
    否
    0.52
    nnnn
    0.52
    AndEndTag
    0.52
    frame
    0.51
    frames
    0.51
    nn
    0.50
    出版年
    0.48
    ne
    0.47
    selho
    0.47
    Activations Density 0.216%

    No Known Activations