© 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. 1-CLT-HP
    7. 15297
    Prev
    Next
    INDEX
    Explanations

    PS

    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
     PS
    -0.75
    mergeFrom
    -0.64
     relieving
    -0.64
     PSC
    -0.64
    ValueStyle
    -0.63
    Gön
    -0.63
    protoc
    -0.63
    throughput
    -0.59
     PSU
    -0.59
    EndProject
    -0.59
    POSITIVE LOGITS
     Тогда
    0.48
    ckeys
    0.43
    B
    0.41
    영어
    0.40
    us
    0.39
     naselje
    0.39
     apos
    0.36
     himself
    0.36
    ed
    0.36
     extremo
    0.36
    Activations Density 0.007%

    No Known Activations