© 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. 0-CLT-HP
    7. 97543
    Prev
    Next
    INDEX
    Explanations

    llar

    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
    antaranya
    -0.68
    gartner
    -0.65
    sendRedirect
    -0.62
     Duterte
    -0.62
     Spain
    -0.61
     Mercer
    -0.60
    ycz
    -0.60
     Hermitage
    -0.59
    hampton
    -0.59
    __':
    -0.59
    POSITIVE LOGITS
    ly
    0.53
     Infórmanos
    0.49
    da
    0.48
    Vezi
    0.47
    Personendaten
    0.47
    ValueGenerated
    0.43
    באנגלית
    0.43
    dics
    0.42
    ละ
    0.42
    DBObject
    0.40
    Activations Density 0.149%

    No Known Activations