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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95209
    Prev
    Next
    INDEX
    Explanations

    survey

    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
     of
    -0.66
     propOrder
    -0.65
    ########.
    -0.64
    homonymie
    -0.59
    StructEnd
    -0.57
    rungsseite
    -0.55
    Controllo
    -0.54
    省市镇
    -0.51
     heil
    -0.49
    новниш
    -0.49
    POSITIVE LOGITS
    uxxxx
    0.58
    biamo
    0.56
    Cubit
    0.56
    YLON
    0.56
     mxArray
    0.53
    AndEndTag
    0.53
    moveToFirst
    0.52
    rigada
    0.52
     MaterialApp
    0.52
     <<<<<<<<<<<<<<
    0.51
    Activations Density 0.002%

    No Known Activations