© 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. 20-CLT-HP
    7. 73652
    Prev
    Next
    INDEX
    Explanations

    phases of projects/studies

    np_max-act-logits · 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
     phase
    -1.80
    phase
    -1.68
    Phase
    -1.43
    PHASE
    -1.42
     PHASE
    -1.41
     Phase
    -1.39
     phases
    -1.34
    phases
    -1.33
     fase
    -1.13
     Phases
    -1.13
    POSITIVE LOGITS
    wa
    0.45
    хова
    0.43
    pa
    0.43
     anla
    0.42
    Sna
    0.42
     swimmer
    0.42
    med
    0.42
    als
    0.42
     kissing
    0.41
    hea
    0.40
    Activations Density 0.011%

    No Known Activations