© 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. 42594
    Prev
    Next
    INDEX
    Explanations

    suffixes

    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
     Bourgoin
    -0.63
    Z
    -0.63
    te
    -0.60
    z
    -0.59
    K
    -0.58
    er
    -0.57
    i
    -0.57
     anhyd
    -0.57
    F
    -0.57
     zirc
    -0.57
    POSITIVE LOGITS
    }))
    0.63
     latest
    0.60
    setupUi
    0.59
    noopener
    0.59
    tvguidetime
    0.58
     same
    0.56
    }));
    0.56
    ffilm
    0.56
     يتيمه
    0.55
    tenths
    0.54
    Activations Density 0.040%

    No Known Activations