© 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. 5-CLT-HP
    7. 2159
    Prev
    Next
    INDEX
    Explanations

    comments

    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
     Kraw
    -0.54
    tagext
    -0.53
    <bos>
    -0.48
     ladders
    -0.46
     esternos
    -0.46
     combustible
    -0.44
     bezeichneter
    -0.43
    MessageOf
    -0.43
    ath
    -0.43
    ocities
    -0.41
    POSITIVE LOGITS
    numerusform
    0.61
    AnimationsModule
    0.59
    SequentialGroup
    0.56
     AttributeSet
    0.55
    IMPORTED
    0.55
    InjectAttribute
    0.54
    putra
    0.53
    usercontent
    0.51
    MockBean
    0.51
    InjectMocks
    0.50
    Activations Density 0.048%

    No Known Activations