© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4701
    Prev
    Next
    INDEX
    Explanations

    but

    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
    ]--;
    -0.76
    脚注の使い方
    -0.58
     the
    -0.54
     intelligence
    -0.52
    boa
    -0.52
     ability
    -0.51
     desire
    -0.49
    йся
    -0.48
    越多
    -0.48
     reality
    -0.47
    POSITIVE LOGITS
     is
    0.71
     was
    0.68
    ьаж
    0.63
     proposée
    0.61
     importado
    0.61
     exists
    0.61
    ArgsConstructor
    0.61
     väli
    0.60
    IsInitialized
    0.59
     stammt
    0.59
    Activations Density 0.002%

    No Known Activations