© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 154
    Prev
    Next
    INDEX
    Explanations

    0

    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
    principalTable
    -0.82
    ьаж
    -0.79
    oredCriteria
    -0.73
     Italijani
    -0.69
    withIdentifier
    -0.69
    ]")]
    -0.68
    verwijspagina
    -0.67
    hyrchwyd
    -0.66
    ViewFeatures
    -0.65
    roffenen
    -0.65
    POSITIVE LOGITS
     dépass
    0.47
     européennes
    0.45
     réfrig
    0.44
     éti
    0.44
     necessariamente
    0.43
    alp
    0.41
     raczej
    0.40
     đồ
    0.40
     végét
    0.39
    perl
    0.38
    Activations Density 0.000%

    No Known Activations