© 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. 5648
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ]")]
    -0.73
     CreateTagHelper
    -0.72
    }\]
    -0.66
    esez
    -0.65
     оригіналу
    -0.64
    ]--;
    -0.64
    ::_('
    -0.64
    });*/
    -0.61
     AttributeSet
    -0.61
    POSITIVE LOGITS
     top
    0.76
     later
    0.73
     back
    0.64
    top
    0.61
     rear
    0.56
    later
    0.53
     late
    0.53
     tops
    0.51
     Top
    0.51
     earlier
    0.51
    Activations Density 0.003%

    No Known Activations