© 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. 5-CLT-HP
    7. 96745
    Prev
    Next
    INDEX
    Explanations

    assistance/functionality

    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
    Spoljašnje
    -0.56
     Taktlose
    -0.54
    styleType
    -0.51
    сылкі
    -0.49
     ProtoMessage
    -0.48
     '\\;'
    -0.47
    ########.
    -0.47
    <bos>
    -0.47
    adpleegd
    -0.45
    puesto
    -0.45
    POSITIVE LOGITS
    %)$
    0.61
     the
    0.60
    uxxxx
    0.59
    
    0.58
     propOrder
    0.56
    ParallelGroup
    0.56
    ).</
    0.55
    amaño
    0.54
     Peat
    0.54
    dtd
    0.52
    Activations Density 0.048%

    No Known Activations