© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 521
    Prev
    Next
    INDEX
    Explanations

    Code, bacteria, and errors

    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
    colgroup
    -0.63
    HostException
    -0.60
     nahilalakip
    -0.60
    Personendaten
    -0.59
    ódz
    -0.59
     Radi
    -0.55
     Fathers
    -0.55
     MonoBehaviour
    -0.54
    SupportActionBar
    -0.54
    kháu
    -0.54
    POSITIVE LOGITS
    Inner
    0.46
     Inner
    0.45
     ba
    0.44
     bq
    0.43
     bassist
    0.42
    ***********/
    0.41
    ัติ
    0.40
     sacré
    0.40
    los
    0.39
    caria
    0.39
    Activations Density 0.001%

    No Known Activations