© 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. 10000
    Prev
    Next
    INDEX
    Explanations

    Zh

    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
     Zh
    -0.58
     Volker
    -0.57
     agency
    -0.48
     Alban
    -0.46
     sign
    -0.46
     agencies
    -0.45
    ]--;
    -0.44
    HIDE
    -0.43
    }})
    -0.42
     agent
    -0.42
    POSITIVE LOGITS
     disambiguazione
    0.88
    IContainer
    0.81
    XmlAccessType
    0.74
    tagHelperRunner
    0.73
    __*/
    0.70
     wireType
    0.70
    ParallelGroup
    0.69
     للاسماء
    0.68
    ✨:
    0.67
    ########.
    0.66
    Activations Density 0.016%

    No Known Activations