© 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. 45541
    Prev
    Next
    INDEX
    Explanations

    os

    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
     Covenant
    -0.77
     covenant
    -0.71
    RegressionTest
    -0.68
    venant
    -0.65
     covenants
    -0.61
    SequentialGroup
    -0.56
     Coven
    -0.54
    WEAK
    -0.48
    arrêter
    -0.46
    hésite
    -0.45
    POSITIVE LOGITS
     nakalista
    0.69
    ngdoc
    0.55
    CreateMap
    0.55
    Personendaten
    0.54
    avro
    0.53
    TypedDataSet
    0.53
    AutoScale
    0.52
    ophanes
    0.51
    ]")]
    0.50
    AndEndTag
    0.50
    Activations Density 0.012%

    No Known Activations