© 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. 0-CLT-HP
    4. 95187
    Prev
    Next
    INDEX
    Explanations

    amid

    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
    mi
    -0.99
     mi
    -0.93
    me
    -0.81
     faced
    -0.81
     m
    -0.71
    facing
    -0.69
     et
    -0.68
    my
    -0.58
    mia
    -0.58
    faced
    -0.57
    POSITIVE LOGITS
     poffible
    0.92
     faſt
    0.89
    ſelves
    0.85
     themſelves
    0.84
    )}
    
    0.84
     Jefus
    0.84
    ")));
    
    0.84
     myſelf
    0.84
     Roskov
    0.84
    ]--;
    0.83
    Activations Density 0.286%

    No Known Activations