© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3082
    Prev
    Next
    INDEX
    Explanations

    punctuation and "and"

    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
    ConstraintMaker
    -1.05
    rungsseite
    -1.04
    WebVitals
    -0.94
     препратки
    -0.89
    }))
    -0.86
     referenties
    -0.83
    +:+
    -0.82
    styleType
    -0.80
     &___
    -0.78
    دانشنامهٔ
    -0.77
    POSITIVE LOGITS
    RequestMapping
    0.43
     material
    0.43
     environment
    0.41
     tele
    0.40
    I
    0.40
    water
    0.39
     land
    0.39
     the
    0.38
    Nin
    0.38
     water
    0.37
    Activations Density 0.003%

    No Known Activations