© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97149
    Prev
    Next
    INDEX
    Explanations

    simply

    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
     jLabel
    -0.63
    DebuggerNonUser
    -0.60
     and
    -0.59
    queryInterface
    -0.54
    BorderFactory
    -0.50
    økt
    -0.50
    BufferException
    -0.50
    >(_
    -0.50
     nakalista
    -0.50
     nhàng
    -0.49
    POSITIVE LOGITS
     HasFactory
    0.59
    ValueStyle
    0.54
    rinfo
    0.50
     reflect
    0.48
     perchè
    0.47
     reflects
    0.46
    aksikan
    0.46
     REPRESENT
    0.46
    onel
    0.45
     representan
    0.45
    Activations Density 0.000%

    No Known Activations