© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91582
    Prev
    Next
    INDEX
    Explanations

    seeker

    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
     wasn
    -0.63
     weren
    -0.52
     hadn
    -0.52
     didn
    -0.51
     BoxDecoration
    -0.50
    fjspx
    -0.50
     had
    -0.49
     felt
    -0.48
    WebServlet
    -0.48
     was
    -0.48
    POSITIVE LOGITS
    frutar
    0.60
     enää
    0.59
    ])).
    0.54
    ])));
    0.54
    ')(
    0.53
    Configurer
    0.52
    __).
    0.52
    ’
    0.49
    jface
    0.49
    '
    0.48
    Activations Density 0.025%

    No Known Activations