© 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. 45564
    Prev
    Next
    INDEX
    Explanations

    comedy or tanks

    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
     Ir
    -0.47
     Her
    -0.47
     Tor
    -0.47
    ]));
    
    -0.47
     Tom
    -0.46
     M
    -0.45
     Lynch
    -0.45
     Gra
    -0.44
    <bos>
    -0.43
     Em
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.75
     asiatique
    0.71
    RectangleBorder
    0.71
     autorytatywna
    0.70
    OGND
    0.68
     condoms
    0.68
    躇
    0.66
     becauſe
    0.66
    ształ
    0.65
    المناصب
    0.65
    Activations Density 0.022%

    No Known Activations