© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40945
    Prev
    Next
    INDEX
    Explanations

    ]

    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
    TemporalType
    -0.53
    "]);
    
    -0.53
     [];
    
    -0.52
    [];
    
    -0.52
     ';
    
    -0.51
    "],
    
    -0.49
    ]();
    -0.49
    !")
    
    -0.48
    IGENCE
    -0.48
     }}-
    -0.47
    POSITIVE LOGITS
    <bos>
    1.48
    ↵
    0.90
    ↵↵
    0.88
    contentLoaded
    0.68
     виправивши
    0.66
    The
    0.63
    <eos>
    0.60
     The
    0.60
    It
    0.60
    “
    0.60
    Activations Density 0.266%

    No Known Activations