© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1002
    Prev
    Next
    INDEX
    Explanations

    periods

    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
    WriteTagHelper
    -0.70
    دانشنامهٔ
    -0.63
    KURZBESCHREIBUNG
    -0.59
    Portály
    -0.55
     createState
    -0.55
    UrlResolution
    -0.55
     Hãy
    -0.53
    #+#
    -0.53
     Offisielt
    -0.53
    اریخ
    -0.51
    POSITIVE LOGITS
    UTERS
    0.56
     senator
    0.50
    Senator
    0.48
    zyden
    0.48
     שוליים
    0.47
    czar
    0.46
     fieldNum
    0.45
    +#+
    0.45
     huile
    0.44
    iprot
    0.44
    Activations Density 0.005%

    No Known Activations