© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5123
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    ↵↵
    -0.81
    ]};
    -0.40
    )}
    
    -0.39
    <eos>
    -0.38
    windowFixed
    -0.37
    fileID
    -0.36
    enderror
    -0.36
    ]})
    -0.36
    WriteAttribute
    -0.33
    }))
    
    -0.33
    POSITIVE LOGITS
    存于互联网档案馆
    0.73
     GoogleFonts
    0.71
    SequentialGroup
    0.70
    PositiveButton
    0.68
    kuuta
    0.68
    MessageState
    0.66
     BorderRadius
    0.63
    afficheront
    0.62
     INTERESAR
    0.62
    RectangleBorder
    0.61
    Activations Density 0.006%

    No Known Activations