© 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. 97202
    Prev
    Next
    INDEX
    Explanations

    greetings

    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
    ()])
    -0.41
    ="#">
    -0.38
    vency
    -0.35
    _();
    -0.35
    ':
    
    -0.32
    herself
    -0.31
    '):
    
    -0.31
    ("*");
    -0.31
    }`;
    -0.31
    HIS
    -0.30
    POSITIVE LOGITS
     sorry
    0.93
     yeah
    0.92
     resourceCulture
    0.90
    SequentialGroup
    0.86
    GEBURTSDATUM
    0.82
     if
    0.82
     it
    0.82
     thank
    0.79
     guys
    0.79
     nahilalakip
    0.79
    Activations Density 0.052%

    No Known Activations