© 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. 5-CLT-HP
    7. 5654
    Prev
    Next
    INDEX
    Explanations

    or

    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
     CreateTagHelper
    -0.82
     >=",
    -0.79
    enumi
    -0.78
    GMENT
    -0.69
    ")){
    -0.65
    ')):
    -0.64
     Pingback
    -0.62
    Sucesor
    -0.60
    ():
    -0.59
    ULATIONS
    -0.58
    POSITIVE LOGITS
    ,
    0.80
     that
    0.64
    ViewFeatures
    0.52
     whether
    0.51
     if
    0.49
     generally
    0.47
     were
    0.46
    /
    0.45
    how
    0.45
    strijden
    0.45
    Activations Density 0.001%

    No Known Activations