© 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. 9134
    Prev
    Next
    INDEX
    Explanations

    science and medicine

    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
    withIdentifier
    -0.59
     gând
    -0.55
     suprême
    -0.52
    ợ
    -0.52
    sprü
    -0.48
     frauen
    -0.47
     stratégique
    -0.46
     réussi
    -0.46
     africain
    -0.45
    psons
    -0.44
    POSITIVE LOGITS
     resourceCulture
    0.69
     nakalista
    0.65
    PhysRevLett
    0.63
    ArrowToggle
    0.63
    ioutil
    0.56
    دانشنامهٔ
    0.56
     wireType
    0.55
    RegistryLite
    0.54
    Apparatus
    0.54
    TestBed
    0.54
    Activations Density 0.012%

    No Known Activations