Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12366
    Prev
    Next
    INDEX
    Explanations

    isolated

    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
    XmlAccessType
    -0.81
    TagMode
    -0.70
    fjspx
    -0.68
    IntoConstraints
    -0.62
    }>;
    -0.60
    Бахар
    -0.59
     betweenstory
    -0.59
    fromnode
    -0.57
     onOptions
    -0.57
    Personendaten
    -0.57
    POSITIVE LOGITS
     esterna
    0.50
     riguarda
    0.48
     ocupa
    0.47
     Añade
    0.47
     urbanas
    0.47
     scattata
    0.46
    ھے
    0.45
     kvar
    0.45
     dupla
    0.44
     unidade
    0.44
    Activations Density 0.070%

    No Known Activations