© 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. 3588
    Prev
    Next
    INDEX
    Explanations

    of

    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
     varying
    -0.67
     different
    -0.56
     depending
    -0.55
     fluctuating
    -0.54
     différentes
    -0.54
     varied
    -0.53
     diferentes
    -0.52
     kadang
    -0.52
     differing
    -0.52
    different
    -0.51
    POSITIVE LOGITS
     صوتيه
    0.82
    AddTagHelper
    0.73
    󠁢
    0.66
    ագրություններ
    0.65
    postIndex
    0.64
    msgTypes
    0.63
     estekak
    0.57
    posób
    0.56
     Wicidata
    0.55
     betweenstory
    0.55
    Activations Density 0.001%

    No Known Activations