© 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. 20-CLT-HP
    7. 74865
    Prev
    Next
    INDEX
    Explanations

    Code snippets/Technical documents

    np_max-act-logits · 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
    ########.
    -0.70
    QByteArray
    -0.69
    RegistryLite
    -0.68
    titleMargin
    -0.64
    principalColumn
    -0.61
     propOrder
    -0.60
    ReusableCell
    -0.58
    newswire
    -0.57
     liné
    -0.57
    Personendaten
    -0.56
    POSITIVE LOGITS
    \{\\
    0.60
    indd
    0.51
    gdx
    0.48
    ISE
    0.46
    XMLSchema
    0.44
    KSI
    0.44
     kel
    0.44
     Misch
    0.43
     ks
    0.42
     revel
    0.42
    Activations Density 0.000%

    No Known Activations