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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13056
    Prev
    Next
    INDEX
    Explanations

    legal acts

    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
    verläs
    -0.49
     ervan
    -0.47
    beto
    -0.45
    onChangeText
    -0.43
     atof
    -0.42
     ब्रेकडाउन
    -0.41
    (&:
    -0.41
     useContext
    -0.41
    Act
    -0.41
    zlich
    -0.40
    POSITIVE LOGITS
    Personendaten
    0.65
     Carriage
    0.60
     ModelExpression
    0.59
    mphony
    0.59
     Protection
    0.59
    tuce
    0.59
    XmlAccessType
    0.59
     Bioaccumulative
    0.57
     Réalisation
    0.57
     esternos
    0.56
    Activations Density 0.002%

    No Known Activations