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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97050
    Prev
    Next
    INDEX
    Explanations

    cellular genetics

    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
     doInBackground
    -0.51
    CROSSTALK
    -0.49
    原始内容存档于
    -0.46
    CreateModel
    -0.43
    PyExc
    -0.41
     оригіналу
    -0.38
    <?
    -0.37
    stage
    -0.36
     MyBatis
    -0.35
    OGND
    -0.35
    POSITIVE LOGITS
     judiciales
    0.65
    󠁴
    0.65
    ILON
    0.64
     ordres
    0.60
     Offensive
    0.59
    Brainz
    0.58
     Popov
    0.57
    ज्ञ
    0.57
    lüssel
    0.57
    Ответить
    0.56
    Activations Density 0.018%

    No Known Activations