© 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. 97407
    Prev
    Next
    INDEX
    Explanations

    Legal/official records

    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
     kasarigan
    -0.85
     שוליים
    -0.81
     autorytatywna
    -0.70
    TagMode
    -0.70
    ValueStyle
    -0.66
     transfieras
    -0.66
    verifyException
    -0.63
    SourceChecksum
    -0.63
    +#+
    -0.62
     EnglishChoose
    -0.62
    POSITIVE LOGITS
     
    0.49
     betegs
    0.47
    setParent
    0.42
    closeConnection
    0.42
    verlust
    0.41
    emailAddress
    0.41
     själ
    0.41
    <eos>
    0.40
    DSP
    0.40
    мера
    0.40
    Activations Density 0.177%

    No Known Activations