© 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. 97236
    Prev
    Next
    INDEX
    Explanations

    research writing

    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
    GRANTED
    -0.73
    e
    -0.70
    verwijspagina
    -0.65
    <eos>
    -0.64
     assimilate
    -0.64
    OGND
    -0.63
     Himo
    -0.62
    NOPQRST
    -0.60
     himo
    -0.59
    FailureListener
    -0.59
    POSITIVE LOGITS
     myſelf
    1.09
     Anſ
    0.98
     Jefus
    0.97
     doubtnut
    0.94
     Houſe
    0.94
     itſelf
    0.93
     Majefty
    0.91
     Theſe
    0.89
     pleaſure
    0.88
     Efq
    0.88
    Activations Density 0.117%

    No Known Activations