© 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. 5-CLT-HP
    7. 93759
    Prev
    Next
    INDEX
    Explanations

    Arbitrary text

    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
     responsibility
    -0.93
    Responsibility
    -0.82
    responsibility
    -0.81
     ansvar
    -0.78
     responsabilidad
    -0.74
     Responsibility
    -0.73
     respon
    -0.71
    responsible
    -0.69
     duty
    -0.68
     duties
    -0.68
    POSITIVE LOGITS
    rénées
    0.69
     protoimpl
    0.68
    tonsoft
    0.67
     MotionEvent
    0.64
    reactivex
    0.63
     MainAxisSize
    0.62
    MessageOf
    0.60
    parsedMessage
    0.59
     SqlDbType
    0.59
    ]")]
    0.58
    Activations Density 0.001%

    No Known Activations