© 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. 5228
    Prev
    Next
    INDEX
    Explanations

    to

    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
     generally
    -0.59
    脚注の使い方
    -0.59
     often
    -0.57
    InputTagHelper
    -0.56
     sometimes
    -0.55
    addPreferredGap
    -0.54
     usually
    -0.52
    HasColumnType
    -0.48
     say
    -0.48
     consider
    -0.48
    POSITIVE LOGITS
    }}/>
    0.61
     be
    0.61
     Theſe
    0.60
    )];
    
    0.60
    __);
    0.59
     gynhyrchwyd
    0.59
    ThemeOverlay
    0.57
    '));
    
    0.56
     ]
    
    0.56
     Efq
    0.55
    Activations Density 0.002%

    No Known Activations