© 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. 91134
    Prev
    Next
    INDEX
    Explanations

    Multi or direction

    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
     targeting
    -0.96
     targeted
    -0.95
     cible
    -0.92
     Targeting
    -0.91
     verticale
    -0.89
     AssemblyProduct
    -0.88
     vectorielles
    -0.83
    
    -0.83
     vectorielle
    -0.82
     target
    -0.82
    POSITIVE LOGITS
     $
    0.52
     I
    0.50
    t
    0.48
    the
    0.48
     van
    0.48
     U
    0.48
     H
    0.48
     O
    0.47
     or
    0.47
    ts
    0.47
    Activations Density 0.057%

    No Known Activations