© 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. 90854
    Prev
    Next
    INDEX
    Explanations

    AB

    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
     AB
    -0.82
    AB
    -0.57
     Mel
    -0.56
    she
    -0.52
    ArgsConstructor
    -0.51
     interrupt
    -0.51
    Mel
    -0.49
    brtc
    -0.47
    bonucleic
    -0.47
    celtic
    -0.46
    POSITIVE LOGITS
     reaſon
    0.79
     ſeveral
    0.74
    setVerticalGroup
    0.73
     purpoſe
    0.73
     pleaſure
    0.70
     Theſe
    0.69
     chofe
    0.68
     myſelf
    0.68
     poffible
    0.68
     poffe
    0.66
    Activations Density 0.182%

    No Known Activations