© 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. 0-CLT-HP
    7. 94295
    Prev
    Next
    INDEX
    Explanations

    legal, medical contexts

    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
    cerin
    -0.58
     AssemblyCompany
    -0.49
    sives
    -0.45
    lielmo
    -0.44
     Guin
    -0.43
    ppi
    -0.43
    CAPS
    -0.42
     usos
    -0.40
    tamen
    -0.40
     pravi
    -0.40
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.82
    
    0.82
    webElementXpaths
    0.76
    ArrowToggle
    0.76
    AndEndTag
    0.76
    tvguidetime
    0.76
    onViewCreated
    0.70
    ########.
    0.68
    stdc
    0.68
    RegressionTest
    0.68
    Activations Density 0.081%

    No Known Activations