© 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. 4-CLT-HP
    7. 1044
    Prev
    Next
    INDEX
    Explanations

    time measurement

    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
     kasarigan
    -0.57
    fjspx
    -0.54
    APORE
    -0.51
     <<<<<<<<<<<<<<
    -0.49
     полиции
    -0.47
     bakgrund
    -0.47
     avanti
    -0.46
    StoreMessageInfo
    -0.46
     šķ
    -0.46
    jspx
    -0.46
    POSITIVE LOGITS
    leben
    0.63
    ]--;
    0.60
    ]]
    0.56
    出版年
    0.56
    reggio
    0.55
    }]
    0.55
     }))
    0.54
     Efq
    0.52
     Caruso
    0.52
     becauſe
    0.52
    Activations Density 0.003%

    No Known Activations