© 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. 0-CLT-HP
    7. 95342
    Prev
    Next
    INDEX
    Explanations

    accrue

    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
     accrue
    -0.69
     ویکی‌آمباردا
    -0.66
    揄
    -0.66
     accru
    -0.65
    ainville
    -0.61
    hips
    -0.60
    AsUp
    -0.60
    ly
    -0.60
     оригіналу
    -0.59
    فایل‌لار
    -0.59
    POSITIVE LOGITS
    bootstrapcdn
    0.60
    TypedDataSet
    0.55
     nakalista
    0.52
     fata
    0.51
     ]
    0.50
    \}\\
    0.50
    o
    0.50
    ape
    0.49
    arion
    0.49
    esac
    0.48
    Activations Density 1.913%

    No Known Activations