© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45623
    Prev
    Next
    INDEX
    Explanations

    Scientific research

    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
    ")));
    
    -0.65
    ])));
    -0.64
     ModelExpression
    -0.60
     **/
    
    -0.54
     &___
    -0.52
    )))));
    -0.52
    Jeografia
    -0.51
     kani
    -0.50
    )));
    
    -0.50
    ))));
    -0.50
    POSITIVE LOGITS
    kuuta
    0.73
    extAlignment
    0.56
    ResumeLayout
    0.56
     bodyParser
    0.53
    brando
    0.53
    den
    0.52
     թվական
    0.52
    GHIJKLM
    0.51
    holds
    0.50
    DockStyle
    0.50
    Activations Density 0.587%

    No Known Activations