© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4933
    Prev
    Next
    INDEX
    Explanations

    of

    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
    "}")
    -0.74
    ')")
    -0.71
    .*")]
    -0.65
    ])):
    -0.63
     مرئيه
    -0.63
    Tembelea
    -0.62
    }}">
    -0.60
    ScopeManager
    -0.60
    $^{\
    -0.59
    }$)
    -0.59
    POSITIVE LOGITS
     heureux
    0.60
     démocr
    0.56
     registrazione
    0.51
     voisins
    0.50
     rayures
    0.50
     formazione
    0.49
     heureuse
    0.48
     feroit
    0.48
     rapides
    0.47
     aveug
    0.47
    Activations Density 0.002%

    No Known Activations