© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5014
    Prev
    Next
    INDEX
    Explanations

    bars

    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
    ()])
    -0.75
    <bos>
    -0.75
    )].
    -0.62
    '])->
    -0.59
    []):
    -0.59
    );*/
    -0.57
    ).</
    -0.57
    ].
    -0.57
    ])).
    -0.57
     }).
    -0.56
    POSITIVE LOGITS
     is
    0.84
    енча
    0.69
     can
    0.66
     refers
    0.62
     היא
    0.61
     has
    0.59
     isn
    0.59
     représentent
    0.57
     rimane
    0.57
    Демографія
    0.57
    Activations Density 0.041%

    No Known Activations