© 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. 5-CLT-HP
    4. 383
    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
     Administrativna
    -0.89
     propOrder
    -0.89
    ]--;
    -0.82
    };*/
    -0.76
    ctez
    -0.74
    }$​
    -0.71
    }\]
    -0.70
    GenerationType
    -0.70
     Signalez
    -0.69
    transQ
    -0.69
    POSITIVE LOGITS
     the
    0.59
    :
    0.56
     an
    0.48
     himself
    0.39
    ↵↵
    0.38
     he
    0.37
     another
    0.37
    _
    0.37
     gegenüber
    0.37
    he
    0.36
    Activations Density 0.001%

    No Known Activations