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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41194
    Prev
    Next
    INDEX
    Explanations

    Post

    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
     varandra
    -0.77
     ouvertes
    -0.74
     pleaſure
    -0.72
     détru
    -0.71
     picioare
    -0.70
     suivantes
    -0.67
     pessoais
    -0.67
     refroid
    -0.65
     suivants
    -0.65
     fédé
    -0.64
    POSITIVE LOGITS
     Bell
    0.56
    RegistryLite
    0.52
    LETED
    0.52
     Hall
    0.50
    ContentLoaded
    0.50
    ConstraintMaker
    0.50
     RS
    0.49
     amb
    0.48
    simmon
    0.48
     Met
    0.47
    Activations Density 0.098%

    No Known Activations