© 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. 43067
    Prev
    Next
    INDEX
    Explanations

    reporter

    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
     reporters
    -0.61
     Reporters
    -0.59
    ی
    -0.59
    i
    -0.55
    er
    -0.55
     })
    -0.54
     reporter
    -0.54
     سكانية
    -0.53
    ])));
    -0.53
    anto
    -0.51
    POSITIVE LOGITS
     viewDidLoad
    0.57
    mosa
    0.56
     dàng
    0.56
    IntoConstraints
    0.55
    exitRule
    0.54
    plain
    0.53
    onViewCreated
    0.53
    Portály
    0.52
    تقاوى
    0.52
     Hukum
    0.52
    Activations Density 0.040%

    No Known Activations