© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97540
    Prev
    Next
    INDEX
    Explanations

    code

    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
     about
    -0.60
    about
    -0.51
    $_['
    -0.51
     verhaal
    -0.46
     Monfieur
    -0.46
    geted
    -0.44
    zional
    -0.43
    zieher
    -0.43
     amounts
    -0.43
     amount
    -0.42
    POSITIVE LOGITS
     Infórmanos
    0.91
     jScrollPane
    0.86
     AssemblyTitle
    0.73
     pinulongan
    0.73
    новниш
    0.70
    YLON
    0.67
    }")]
    0.63
     Italijani
    0.62
    ьаж
    0.61
    ,:);
    0.60
    Activations Density 0.144%

    No Known Activations