© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 94997
    Prev
    Next
    INDEX
    Explanations

    it

    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
    !
    -0.48
     make
    -0.44
    |
    -0.42
     made
    -0.41
    <eos>
    -0.40
     pre
    -0.40
     het
    -0.38
    >−
    -0.38
    /}{
    -0.37
     de
    -0.37
    POSITIVE LOGITS
     pleaſure
    1.02
     leaſt
    1.02
     Anſ
    0.99
     ſeveral
    0.95
     poffible
    0.93
     purpoſe
    0.93
     myſelf
    0.92
     themſelves
    0.92
     ſtate
    0.91
     ſen
    0.88
    Activations Density 0.001%

    No Known Activations