Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73848
    Prev
    Next
    INDEX
    Explanations

    Organization, Department, School descriptions

    np_max-act-logits · 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
    \{\\
    -0.50
    (:,:,
    -0.49
    Hochspringen
    -0.47
    ProgressHUD
    -0.47
    WriteHeader
    -0.45
    AutoScale
    -0.44
     بخوانید
    -0.44
    transQ
    -0.43
    ]!='
    -0.43
    ########.
    -0.42
    POSITIVE LOGITS
     Office
    0.89
     Center
    0.88
     Division
    0.88
     School
    0.84
     Department
    0.74
     Centre
    0.74
    Division
    0.67
    Office
    0.65
     College
    0.63
     Bureau
    0.63
    Activations Density 0.007%

    No Known Activations