© 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. 4636
    Prev
    Next
    INDEX
    Explanations

    really

    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
    ,
    -0.73
     –
    -0.52
     (
    -0.46
     -
    -0.45
     —
    -0.43
    <eos>
    -0.41
     --
    -0.41
     ‘
    -0.40
     jorden
    -0.40
     /
    -0.40
    POSITIVE LOGITS
    .[/
    0.96
     myſelf
    0.95
    AndEndTag
    0.93
     itſelf
    0.93
     ſind
    0.90
     ་་
    0.90
     Houſe
    0.88
     ―――――
    0.87
    httphttps
    0.87
    ."]
    0.86
    Activations Density 0.005%

    No Known Activations