© 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. 5179
    Prev
    Next
    INDEX
    Explanations

    wanting to do something

    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
    ########.
    -0.60
    >{@
    -0.55
    Espèce
    -0.50
     cathe
    -0.50
    }}],
    -0.50
     depred
    -0.49
    Sucesor
    -0.49
     Entdecken
    -0.49
     olives
    -0.49
     fluids
    -0.49
    POSITIVE LOGITS
    TagMode
    0.59
    DockStyle
    0.57
    Parcelize
    0.54
     IndexPath
    0.53
    ftagPool
    0.51
     lenker
    0.51
    躇
    0.51
    rypt
    0.50
     كومونز
    0.50
    avond
    0.50
    Activations Density 0.002%

    No Known Activations