© 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. 41189
    Prev
    Next
    INDEX
    Explanations

    missiles

    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
     radical
    -0.70
    found
    -0.59
    um
    -0.51
    land
    -0.51
    sele
    -0.50
    mon
    -0.50
    radical
    -0.49
    kok
    -0.49
    xl
    -0.48
    ])):
    -0.48
    POSITIVE LOGITS
    complexContent
    0.79
     AssemblyCulture
    0.79
     zelve
    0.76
     démission
    0.75
     Réponses
    0.73
    ItemBackground
    0.73
     automatico
    0.72
     zoude
    0.72
     démocr
    0.72
    Дереккөздер
    0.71
    Activations Density 0.493%

    No Known Activations