© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5848
    Prev
    Next
    INDEX
    Explanations

    code/data punctuation

    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
    enseur
    -0.55
    CBM
    -0.55
    κίνη
    -0.55
     Rubén
    -0.53
    ujin
    -0.53
     MOL
    -0.53
     veta
    -0.52
     juſ
    -0.52
    όμε
    -0.52
    rami
    -0.52
    POSITIVE LOGITS
    Enllaces
    0.44
    NewRow
    0.43
    asList
    0.43
    లాలు
    0.41
     beginnetje
    0.40
    ngiliz
    0.39
     dialami
    0.39
     Formations
    0.39
    Források
    0.38
     Breaks
    0.38
    Activations Density 0.001%

    No Known Activations