© 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. 4521
    Prev
    Next
    INDEX
    Explanations

    Research studies with numbers

    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
     skak
    -0.47
     Schal
    -0.46
    Cześć
    -0.46
     málaga
    -0.46
     possam
    -0.45
     Milliarden
    -0.45
    談社
    -0.44
    sizeCache
    -0.44
    Whereas
    -0.44
     podamos
    -0.43
    POSITIVE LOGITS
    UserScript
    0.84
     years
    0.68
    verifyException
    0.68
     nahilalakip
    0.63
    enumii
    0.61
    Jegyzetek
    0.60
     pinulongan
    0.58
    Espèce
    0.55
     ErrIntOverflow
    0.54
    requestCode
    0.54
    Activations Density 0.002%

    No Known Activations