© 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. 5-CLT-HP
    7. 4731
    Prev
    Next
    INDEX
    Explanations

    conclusion indicators

    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
     deserves
    -0.73
    ]--;
    -0.67
     can
    -0.65
     constitutes
    -0.63
     represents
    -0.62
     cannot
    -0.62
    [])
    -0.62
     helps
    -0.60
     makes
    -0.59
     warrants
    -0.59
    POSITIVE LOGITS
    oredCriteria
    0.61
     mesmas
    0.54
    NameInMap
    0.52
    former
    0.49
     artificiales
    0.49
    also
    0.49
     stesse
    0.49
     revenus
    0.48
     AssemblyVersion
    0.48
    lardır
    0.48
    Activations Density 0.001%

    No Known Activations