© 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. 20-CLT-HP
    7. 77291
    Prev
    Next
    INDEX
    Explanations

    factors

    np_max-act-logits · 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
     courants
    -0.92
    IntoConstraints
    -0.82
     démocr
    -0.79
    UnsafeEnabled
    -0.78
     صوتيه
    -0.77
     découver
    -0.75
     enfans
    -0.74
     feroit
    -0.72
    webElementXpaths
    -0.71
     américains
    -0.69
    POSITIVE LOGITS
     accountable
    0.48
     determine
    0.47
     take
    0.43
    matchCondition
    0.42
     answer
    0.42
     essentially
    0.41
     decide
    0.40
    ILITIES
    0.40
     }],
    0.39
    ets
    0.39
    Activations Density 0.003%

    No Known Activations