© 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. 0-CLT-HP
    7. 1953
    Prev
    Next
    INDEX
    Explanations

    No

    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
     pinulongan
    -0.94
     ſche
    -0.91
    adaptiveStyles
    -0.91
     continúas
    -0.89
     rhestr
    -0.88
     Efq
    -0.88
    ^(@)
    -0.87
     houſe
    -0.86
     myſelf
    -0.83
     ſever
    -0.82
    POSITIVE LOGITS
    ,
    0.87
     no
    0.82
     an
    0.59
     and
    0.57
     the
    0.56
     
    0.55
     No
    0.55
     both
    0.53
     es
    0.52
     mat
    0.52
    Activations Density 1.266%

    No Known Activations