© 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. 14401
    Prev
    Next
    INDEX
    Explanations

    ships and shipwrecks

    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
    urlpatterns
    -0.72
    endpush
    -0.72
    Бахар
    -0.67
    webElementGuid
    -0.64
    ExtendWith
    -0.64
    DebuggerStep
    -0.63
    multer
    -0.63
    bumptech
    -0.60
    vancing
    -0.60
    Numerade
    -0.60
    POSITIVE LOGITS
    Jeografia
    0.50
     mundiales
    0.47
     löytyy
    0.46
    soever
    0.44
     stră
    0.43
     tarjo
    0.43
     păr
    0.42
     encantado
    0.42
     Phoen
    0.42
    out
    0.42
    Activations Density 0.016%

    No Known Activations