© 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. 96398
    Prev
    Next
    INDEX
    Explanations

    quantity

    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
    хьтан
    -0.57
     dAtA
    -0.56
    InvalidProtocol
    -0.55
     but
    -0.52
    ########.
    -0.50
    verwijspagina
    -0.49
    发表于
    -0.46
    談社
    -0.46
     võib
    -0.45
    خوش
    -0.44
    POSITIVE LOGITS
     others
    0.76
     other
    0.68
    #+#
    0.65
     ALSO
    0.65
     also
    0.65
     Also
    0.64
     another
    0.61
     OTHERS
    0.61
     either
    0.61
     Others
    0.60
    Activations Density 0.021%

    No Known Activations