© 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. 1-CLT-HP
    7. 45703
    Prev
    Next
    INDEX
    Explanations

    compressor

    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
     hiszen
    -0.44
    kapet
    -0.42
     liné
    -0.40
    ork
    -0.39
    tista
    -0.39
    пар
    -0.39
     frères
    -0.37
     Farm
    -0.37
     pharmacie
    -0.37
     remercier
    -0.37
    POSITIVE LOGITS
    DockStyle
    0.92
    DeleteBehavior
    0.91
     صوتيه
    0.88
    parsedMessage
    0.85
     Numerade
    0.79
    ]),
    0.75
     feveral
    0.73
    CodedInputStream
    0.73
     defStyleAttr
    0.73
    CloseOperation
    0.72
    Activations Density 0.038%

    No Known Activations