© 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. 3421
    Prev
    Next
    INDEX
    Explanations

    ”

    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
    bitField
    -0.44
    UnusedPrivate
    -0.44
     GetEnumerator
    -0.43
    PlayerPrefs
    -0.42
     op
    -0.40
     Numerade
    -0.40
    الحياه
    -0.39
     Coles
    -0.39
    opo
    -0.38
    θεν
    -0.38
    POSITIVE LOGITS
    UnsafeEnabled
    0.62
    httphttps
    0.57
    KommentareTeilen
    0.57
     JpaRepository
    0.57
    __*/
    0.57
    principalTable
    0.56
     InputDecoration
    0.56
     Anarch
    0.55
     Monfieur
    0.54
     ragione
    0.54
    Activations Density 0.002%

    No Known Activations