© 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. 4-CLT-HP
    7. 4515
    Prev
    Next
    INDEX
    Explanations

    semantic transformation

    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
    WriteAttribute
    -0.71
     AssemblyCulture
    -0.68
     doInBackground
    -0.66
    DockStyle
    -0.61
    طلحات
    -0.58
    Personendaten
    -0.57
    ustimmung
    -0.57
    passage
    -0.57
    :+:
    -0.54
    Tikang
    -0.53
    POSITIVE LOGITS
    minecraftforge
    0.50
    .*")]
    0.49
     dementia
    0.47
     <>",
    0.46
    pim
    0.43
    ri
    0.43
     հղումներ
    0.43
    an
    0.42
     HasFactory
    0.41
     Dementia
    0.41
    Activations Density 0.003%

    No Known Activations