© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4442
    Prev
    Next
    INDEX
    Explanations

    world news

    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
     betweenstory
    -0.70
    المكان
    -0.61
    tanleria
    -0.58
     Италијани
    -0.54
     SEDS
    -0.53
    디오
    -0.51
     ddelweddau
    -0.50
    tania
    -0.50
    mtrl
    -0.49
     Leurs
    -0.48
    POSITIVE LOGITS
    SequentialGroup
    0.73
     समीक्षाएं
    0.67
    +:+
    0.61
    MemoryWarning
    0.61
    ReusableCell
    0.58
    ]")]
    0.56
    thought
    0.54
     églises
    0.52
     GenerationType
    0.52
     quoi
    0.52
    Activations Density 0.002%

    No Known Activations