© 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. 5-CLT-HP
    4. 3086
    Prev
    Next
    INDEX
    Explanations

    code/math

    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
    locene
    -0.56
    childrens
    -0.56
     descre
    -0.55
    kursi
    -0.53
     SF
    -0.52
     Zapo
    -0.51
     Schna
    -0.50
    يكب
    -0.50
    prilis
    -0.50
    uza
    -0.49
    POSITIVE LOGITS
     utafitiHapana
    0.67
    Personendaten
    0.54
    ]))
    
    0.54
    ])),
    0.54
    ,))
    0.53
    SBATCH
    0.52
     AttributeSet
    0.52
    ]));
    
    0.52
     للمعارف
    0.52
    ")));
    
    0.52
    Activations Density 0.001%

    No Known Activations